Compare commits

..

132 Commits

Author SHA1 Message Date
4964849397 fix(agents): вернуть opt-in 'session sync: write to mappa' в AGENTS.md\n\nСтроку вырезал коммит 79adaf9 «канон-блок — краткая суть гейтов вместо обрубков» (task:3017)\nпри переработке проекции канон-блока. Без неё pi-расширение (mappa.ts isOptedIn) не поднимает\nlive-ingest → сессии проекта не пишутся в mappa.\n\nВосстановлено на исходную позицию (контекст из вырезавшего коммита). 2026-09-19 16:44:14 +03:00
c5eee95460 docs(AGENTS.md): ре-прогон канон-блока на mappa-setup@0.2.8 (task:3030)
Тело блока — 0 изменений (рендер == живая курированная форма, issue:110);
нормализован стык (контракт mergeCanonBlock, task:3023).
2026-09-19 09:52:30 +03:00
79adaf928d docs(AGENTS.md): канон-блок — краткая суть гейтов вместо обрубков (task:3017) 2026-09-18 22:12:27 +03:00
b51657bfe4 docs(AGENTS.md): канон-блок — краткая суть гейтов вместо обрубков (task:3017) 2026-09-18 21:58:28 +03:00
48fa29e9dc docs(AGENTS.md): канон-блок — краткая суть гейтов вместо обрубков (task:3017) 2026-09-18 21:25:56 +03:00
65a2518a5e docs(canon): канон-блок AGENTS.md из живого shared-среза (task:2882)
Блок перегенерирован писателем кэша, поставленным в mappa-setup 0.2.6
(--gen-canon-block: живой shared → кэш .mappa/share/ → блок из ТОГО ЖЕ среза).

- строка Entity → runbook снова несёт полный каталог типов из runbooks/index
  (issue, intent, requirements, plan, comment, tag, attachment, release,
  brainstorm, agent, repo, project, skill, entity, sched) — до этого в блоке
  оставалась усечённая карта;
- Canon version — версия КАНОНА (canon/*), не максимум по методологии/ранбукам.
2026-09-18 00:28:08 +03:00
84e28c5d1c docs: канон-блок AGENTS.md — Г2 v4 (адресация about/thread) + сняты junk mail-строки (task:2993) 2026-09-17 23:41:40 +03:00
607a475e28 feat(ops-browser): скил своего скрытого браузера (профиль+CDP+хендофф) в каталог; маппинг в Hermes-дерево; строки в README 2026-09-12 12:30:05 +03:00
252e22ec80 fix(browser-operator): PID аренды только настоящий (/proc/$$/winpid), driver.lock руками не трогать 2026-09-11 23:31:37 +03:00
ac0c41feb8 chore: .gitignore — .mappa/share/ (кэш bootstrap, генерируется) 2026-09-11 23:13:32 +03:00
314b15ea25 feat(browser-operator): скил-водитель для браузера оператора (канал по харнессу + аренда)
- skills/browser-operator/SKILL.md: канал по харнессу (Hermes browser_exec / pi тул browser /
  CC chrome-devtools), аренда «один водитель за раз», границы человек/агент, рецепты тяжёлых
  страниц (fetch внутри вкладки, паузы в Python, AX-дерево для кликов), таблица антипаттернов
- основание — RED-прогон без скила (2026-09-11): агент ушёл в curl + browser_cookie3 + ввод
  пароля мимо канала и аренды и не знал адрес кабинета ЧипДипа (/order/list, а не /cabinet)
- browser-cdp 0.1.1: разведены зоны (личные кабинеты оператора -> browser-operator)
- hermes/mapping.yaml: browser-operator (auto/software-development) — сейчас конвертер
  красный из-за 14 ранее незамапленных скилов, это отдельная находка
- README + README.ru: строка провенанса
2026-09-11 22:12:21 +03:00
c310ada38d chore(marker): .mappa/config.yaml — git_host (issue:30, task:2558) 2026-09-06 16:39:41 +03:00
5c726eb5ec docs(project-bootstrap): согласовать doc с mappa-agnostic шаблоном (task:2024 review-minor)
Inline-зеркало шаблона, пояснение об инъекции, строка session sync в
deps-check, README. Строка session handoff (легаси) оставлена — актуальна
для проектов, несущих её в AGENTS.md.
2026-09-02 14:38:35 +03:00
d2059b42bd refactor(project-bootstrap): mappa-agnostic шаблон AGENTS.md — инъекция mappa-триггеров через mappa-bootstrap (task:2024)
Шаблон больше не хардкодит mappa-триггеры (inbox monitor, use project wiki,
use task management system, check across all projects, session handoff убраны).
Kanonicheskiy набор (вкл. session sync) инжектится при создании/апгрейде
через mappa-bootstrap (install.sh --triggers). Step 5.7.2: верификация → инъекция.
2026-09-02 14:34:06 +03:00
2707ba48b5 Revert "chore(project-bootstrap): добавить триггер session sync: write to mappa в шаблон AGENTS.md (task:2015)"
This reverts commit 9c969cefb9.
2026-09-02 13:47:22 +03:00
9c969cefb9 chore(project-bootstrap): добавить триггер session sync: write to mappa в шаблон AGENTS.md (task:2015) 2026-09-02 13:39:06 +03:00
37f617a461 chore(marker): .mappa/config.yaml — маркер mappa-проекта (схема v1) 2026-09-02 09:34:15 +03:00
ccac87200f refactor(1900): mappa-vitya-* → mappa-kzntsv-* в project-bootstrap (бренд kzntsv.dev); ссылка на легаси-репо помечена 2026-09-01 21:28:43 +03:00
b1cc0439a7 chore(dist): rebuild — review-kit-pi-method v0.1.2 (CC-спавн) + синк остальных 2026-09-01 15:25:30 +03:00
3f78c54dd2 feat(review-kit-pi-method): CC-спавн субагент-ревьюера (claude-deepseek) — live-проверен 2026-09-01
v0.1.1→0.1.2: секция CC в Cross-agent — флаги изоляции (--tools '' --disable-slash-commands --no-session-persistence), модель deepseek-v4-flash-vision-exp, обёртка claude-deepseek. Из письма .workshop (task:1849 контекст review-механизмов).
2026-09-01 15:24:41 +03:00
ddcb552601 chore(project-create): relocated to mappa/skills-core (task:1595) — это mappa core-скил, канон в монорепо victor/mappa 2026-08-30 02:04:49 +03:00
74fdbe8070 fix(project-create): уточнить What-NOT-to-do — репо без регистрации = omission, не порядок (review 1594) 2026-08-30 01:58:08 +03:00
973e59b083 feat(project-create): v0.3.0 — путь создания репо = выбор оператора (шаг 2, Hard rule 2: не регистрировать до репо) [agensyn-урок 2026-08-29] 2026-08-30 01:57:45 +03:00
c09901f9a6 feat(project-bootstrap): .mappa маркер при создании проекта — шаг 5.8 + рендер-ассет, project-create шаг 5.5 (wiki:3340, task:1583) [v3.3.0] 2026-08-29 23:55:18 +03:00
e2f2e3a342 chore(1459): убраны mappa-vitya-* из skills-репо — перенесены в victor/mappa-vitya-skills
- удалены skills/mappa-vitya-brainstorming + mappa-vitya-project-discipline
- README: убрана строка provenance mappa-vitya-brainstorming
- project-bootstrap: ссылки на mappa-vitya-project-discipline → victor/mappa-vitya-skills
- правило уведомлений (.admin) уже зафиксировано в целевом репо (3b4d51c)
2026-08-29 23:36:09 +03:00
b529503def docs(1488): переименования после консолидации mappa-расширений — ссылки на mappa.ts
- skills/session-health/SKILL.md: поллер → extensions/mappa.ts (секция session-health, task:1486)
- .wiki/concepts/pi-extension-headless-ritual.md: session-close-ritual → mappa.ts (исторически отдельный файл)
- критерий 6 requirements:1: старые имена в docs/skills/wiki = 0, кроме исторических записей
2026-08-29 09:05:16 +03:00
031268333e fix(1440): review-фикс 1437 — 'review-umbrella' → 'review task (paired or umbrella)' [skip-tdd: visual] 2026-08-28 15:18:45 +03:00
e499a69bd0 fix(1436): review-routing — парные ИЛИ зонтик, не BOTH (оператор) 2026-08-28 14:18:24 +03:00
247abbbf12 feat(mappa-vitya-project-discipline): rename project-discipline → mappa-vitya-project-discipline, Rule 1 → mappa-canon, +4 mappa rules; project-bootstrap: drop legacy trigger [v1.0.0] 2026-08-27 22:37:47 +03:00
e3f20193f0 docs(project-discipline): Rule 4 — механизм push-гейта переписан (on-record + explicit) [v0.2.2] 2026-08-27 21:33:21 +03:00
1b0118d254 feat(mappa-vitya-brainstorming): brainstorm METHODOLOGY for a mappa zone [v0.1.0]
- Behavior layer (not mechanics): how to run a storm in a mappa zone, keep
  the running-record buffer, judge maturity by criterion (not feeling), and
  route the matured result (spec → wiki concept, tasks, reviews).
- Promotion MECHANICS delegated to mappa-brainstorm-promote (not duplicated).
- Specs/knowledge → mappa wiki concept; mappa-knowledge required before wiki.
- Multiple impl tasks → paired <slug>-review + umbrella <topic>-review,
  non-implementer reviewer; ask who implements (boss does not implement).
- Notify affected projects via inbox_send.
- Reviewed by clean-context non-implementer reviewer; all findings closed
  (description → pure triggers, no 'what should we build' conflict, explicit
  promote boundary, zero-impl-task case, mandatory mappa-knowledge).
- README provenance table updated.
2026-08-27 21:09:12 +03:00
4f8e12aedf docs: mappa-bootstrap sweep — убрать мёртвые scripts/install.sh mappa-* (task:1340, 1339-пробел) 2026-08-27 18:07:41 +03:00
7504b09b87 fix(project-bootstrap): мёртвые ссылки mappa-* → делегирование скилу mappa-bootstrap (репо mappa, wiki:3265, task:1339); v3.0.3→3.1.0 2026-08-27 17:45:06 +03:00
5301e853f7 chore(1328): дедуп mappa-скилов из skills/skills + dist — канон теперь в mappa
- удалены 8 mappa-* + report-mappa-issue из skills/skills (источник — mappa/skills/)
- удалены соответствующие dist/mappa-*.skill архивы
- skills/skills остаётся только для общих скилов
- чужие WIP (update-skills, using-markitdown dist) не тронуты
2026-08-27 14:42:12 +03:00
cf8d574c9f fix(project-create): правки по review-субагенту — шаг 4 (где+имя), шаг 5 (локальная ФС) [1304] 2026-08-26 22:58:27 +03:00
621eacc808 feat(skill): project-create v0.1.0 — mappa-сторона создания проекта (спросить адрес → pre-flight → mappa+репо одновременно → папка → bootstrap) 2026-08-26 22:57:39 +03:00
4b4339733c fix(project-bootstrap): Search rule — расширенная формулировка по review-субагенту (запрет не-gitignore-aware обхода, rg --no-ignore, ag/ack/find-exec-grep)
v3.0.2 → v3.0.3 (review task:1234 findings).
2026-08-26 11:53:52 +03:00
90861fc197 fix(project-bootstrap): шаблон AGENTS.md — Search rule (запрет grep -r по node_modules, прецедент 3701s vs rg 0s)
v3.0.1 → v3.0.2. Новые проекты наследуют запрет: '⛔ Never grep -r/find-walk trees containing node_modules — use rg (gitignore-aware)'. Инцидент .admin 2026-08-26 (task:1233).
2026-08-26 11:45:16 +03:00
6fcb8a8adb fix(skills): правки по review-субагенту — stale canon, деплой-гейт self-assign, wiki_update key
mappa-task-work v1.5.1:
- 'Refs and ids': internal id 'for addressing in tools' убрано (канон 1221)
- Deploy gate: .admin-таска для self-assigned создаётся через mappa-delegation (кто создаёт — явно)
- Нумерация Phase 3: 5/6/7 (был дубль 6)

mappa-knowledge v1.5.3:
- MCP-таблица wiki_update: id = num | ref wiki:N | uuid
- 'not ids' → 'not internal ids'
2026-08-26 11:40:37 +03:00
cbba01f1e1 fix(skills): канон адресации num/ref/uuid вместо internal id (task:1221) + парная review через субагента + деплой-гейт
mappa-task-work v1.5.0:
- entity_get/task_get: uuid | task:NNN | bare num (голое число = num, канон 1221)
- Phase 3.5: self-assigned impl-таска создаёт парную review; ревью через субагента (review_subagent/review-kit-pi-method), не сам
- Phase 3.6: деплой-гейт (close → review → follow-up done → deploy, через .admin)

mappa-brainstorm-promote v1.10.0:
- brainstorm_id = num | ref | uuid; PATCH /brainstorm/:id num|ref|uuid
- 'bare numbers → 400' убрано (этап A task:1221 задеплоен)

mappa-knowledge v1.5.2:
- wiki_update: num/ref/uuid вместо internal id; addressing slug → num/ref/uuid

mappa-delegation v1.4.0:
- деплой-гейт (target .admin, ранбуки/секреты служебные)
- уведомление всех затронутых проектов письмом (кроме себя)
2026-08-26 11:37:38 +03:00
931330bf31 feat(skill): writing-skills v0.2.0 — placement rule: проектный скил → .agents/skills/ (cwd), не ~/.agents/skills/ и не каталог 2026-08-26 10:18:27 +03:00
e81217388e feat(skill): code-search v0.1.0 — rg-first code search (RED: grep -r 15min+ hang → GREEN: rg 0s; routing rg/git-grep/repo_read/grep_audit) 2026-08-26 08:41:38 +03:00
c6dfa9349d feat(skill): mappa-presentation v1.1.0 — серверные display/card verbatim (UTC+Z), fallback до деплоя
- серверные display/card (task:1176/1177, репо 0bf09c6): копировать verbatim, row → display / карточка → card
- даты в серверных полях — UTC+Z (row YYYY-MM-DD / card YYYY-MM-DDTHH:MMZ), без конвертации
- шаблоны — fallback-канон до деплоя v0.20.0 (проверять /health)
- принцип 5 (даты) переписан: серверные поля verbatim / fallback — локальное время
2026-08-25 23:34:14 +03:00
3ea7e53f99 feat(skill): mappa-brainstorm-promote v1.9.0 — два пути (promote/close), forward-ref [[brainstorm:N]], критерий завершения
- task_create из буфера несёт [[brainstorm:N]] (ребро на write, same-project)
- close-путь (step 5b): уже-завершённый буфер → проверка тасок + финальный entry + status=archive
- финальный entry со списком [[task:N]] (step 8b)
- критерий: буфер done ⇔ все action-items поставлены ∧ все таски done (вкл. review-зонт) — wiki:3188 .workshop
- триггеры: «закрой буфер», «архивируй буфер», close the buffer
2026-08-25 23:34:14 +03:00
dd9e38b2ee feat(skills): mappa-presentation — display canon for mappa entities
Agents rendered mappa entities ad-hoc (raw JSON, random fields) — human
re-asked 'give me details'. New skill fixes the presentation layer:
row (lists) + card (single entity) templates per type, fixed field order,
local-time dates (UTC storage, agent converts), full refs, never raw JSON.
mappa-task-work/messaging/knowledge now point to it (mandatory format);
versions bumped (1.4.1/1.4.1/1.5.1).
2026-08-25 22:39:46 +03:00
d0b8041891 chore(meta): file-based meta channel closed (canon=mappa) — stubs .wiki/.tasks/.agents-inbox + AGENTS.md cleanup (2026-08-25) 2026-08-25 22:07:19 +03:00
5675da52a7 chore(skills): remove meta-mcp skills (file channel closed, canon=mappa)
- delete using-projects-meta, setup-projects-meta (repo+targets)
- delete meta-host-routing, setup-tasks, setup-wiki (targets)
- project-bootstrap: projects-meta refs → mappa (Step 8 registry, triggers, auth fallback), v3.1.0
- update-skills: drop projects-meta-mcp rebuild step, v0.3.0
- README: bootstrap delegation .wiki/.tasks → mappa registration
2026-08-25 22:03:17 +03:00
5b5085eb80 fix(skills): entity_get/task_get на uuid/ref-ключи — контракт task:1067 (голые internal id → 400)
- mappa-task-work 1.3.0→1.4.0: read-ключи uuid/task:NNN, close/update берут internal id из ответа
- mappa-brainstorm-promote 1.7.0→1.8.0: entity_get по brainstorm:N/uuid, internal id для promote из ответа
- mappa-messaging 1.3.0→1.4.0: резолв по uuid/ref [skip-tdd: visual] (task:1093)
2026-08-25 17:56:25 +03:00
b6b8560fc0 fix(skills): project-bootstrap 3.0.0→3.0.1 — unified skill detection paths 5.6/5.7.3 (task:1091, finding ревью 1089) 2026-08-25 17:51:10 +03:00
1ca1f2f868 feat(skills): project-bootstrap 2.2.0→3.0.0 — модуль mappa-bootstrap-project (connect + конвенции + методика-install + manifest) [skip-tdd: visual] (task:1088, wiki:2672 решение 4) 2026-08-25 17:46:58 +03:00
d1adf7806d fix(skills): mappa-brainstorm-promote 1.7.0 — trigger dedup + English 'publish to wiki' (review task:1090 finding) 2026-08-25 17:45:31 +03:00
cb65d377eb docs(skills): mappa-delegation — annotate intentional bilingual placeholder in covering-letter template (task:1086) 2026-08-25 17:43:48 +03:00
8cfd46eb09 docs(skills): mappa-brainstorm-promote 1.6.0→1.7.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:37 +03:00
195de4b8e6 docs(skills): mappa-task-work 1.2.0→1.3.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:37 +03:00
0177d46101 docs(skills): mappa-messaging 1.2.0→1.3.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:36 +03:00
bf807f232b docs(skills): mappa-knowledge 1.4.1→1.5.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:35 +03:00
76ff6ad3fc docs(skills): mappa-delegation 1.2.0→1.3.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:35 +03:00
e91eb701aa docs(skills): mappa-closing-ritual 1.2.0→1.3.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:34 +03:00
271fcfae93 docs(skills): mappa-session-orient 1.0.1→1.1.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:34 +03:00
41a805d66c docs(skills): report-mappa-issue 0.1.0→0.2.0 — English translation, bilingual triggers (task:1086) 2026-08-25 17:42:33 +03:00
b7ac5cd5a6 docs(skills): mappa-session-orient 1.0.1 — CC-хук operator: CC headless несёт operator:vitya (task:1061) 2026-08-25 14:07:41 +03:00
8c19294a28 fix(skills): mappa-knowledge 1.4.1 — frontmatter type: source → summary (ревью #1058) 2026-08-25 13:59:12 +03:00
805077902d feat(skills): wiki bucket sources/ → summaries/ — mappa-knowledge, project-bootstrap, using-markitdown, using-projects-meta (+README) (решение 2026-08-24) 2026-08-25 13:52:58 +03:00
0ed7060116 docs(wiki): index — Sources → Summaries (решение 2026-08-24) 2026-08-25 13:52:58 +03:00
3806b0407b docs(wiki): schema — bucket sources/ → summaries/ (решение 2026-08-24) 2026-08-25 13:52:58 +03:00
dc2cd0e522 fix(skills): mappa-brainstorm-promote 1.6.0 — review findings (#1052): brainstorm_update для summary, порядок валидации, failure modes (entity_search/inbox_send), admin_status убран 2026-08-25 13:52:58 +03:00
a1f12fcdd4 feat(skills): mappa-brainstorm-promote 1.6.0 — brainstorm-сущность, общий механизм mappa (без workshop-специфики и storm-сокращений) (#1066) 2026-08-25 13:52:58 +03:00
aabf8da806 feat(skills): mappa-brainstorm-promote 1.5.0→1.6.0 — storm-канал: буфер = mappa storm-сущность, промоут через storm_promote, project-agnostic (#1066) 2026-08-25 13:52:58 +03:00
e31921b7a7 meta(tasks): close [mappa-brainstorm-promote-storm-channel] in OpeItcLoc03/skills 2026-08-25 08:05:43 +00:00
65330605d8 meta(tasks): update [mappa-brainstorm-promote-storm-channel] in OpeItcLoc03/skills 2026-08-25 07:18:23 +00:00
7cd1384c98 meta(tasks): update [mappa-brainstorm-promote-storm-channel] in OpeItcLoc03/skills 2026-08-25 07:11:05 +00:00
d96af7f737 meta(tasks): update [mappa-brainstorm-promote-storm-channel] in OpeItcLoc03/skills 2026-08-25 07:08:34 +00:00
197007f21e meta(tasks): create .tasks/2026-08-25-01066-mappa-brainstorm-promote-storm-channel.md in OpeItcLoc03/skills 2026-08-25 06:00:39 +00:00
564adb140e meta(tasks): create [mappa-brainstorm-promote-storm-channel] in OpeItcLoc03/skills 2026-08-25 06:00:39 +00:00
9b606f79bb feat(skills): frontmatter-summary дисциплина (wiki:2661) + wiki.search в MCP-поверхности [skip-tdd: visual]
- mappa-knowledge 1.2.0→1.3.0: карточный поиск wiki.search в MCP-таблице (entity_search остаётся как fallback полных тел); блок Frontmatter-summary — при create/update/promote писать summary: одной строкой в frontmatter
- mappa-brainstorm-promote 1.4.0→1.5.0: summary-дисциплина при wiki_create спеки (service channel)
- dist пересобраны
2026-08-25 08:58:01 +03:00
c213997e1d feat(skills): сверка mappa-* скилов с деплоем — репо догнал установленные 1.2.0/1.4.0 (интерактивный контракт wiki:2660) [skip-tdd: visual]
- mappa-task-work 1.1.0→1.2.0, mappa-delegation 1.1.0→1.2.0, mappa-knowledge 1.1.0→1.2.0, mappa-messaging 1.1.0→1.2.0, mappa-brainstorm-promote 1.3.0→1.4.0, mappa-closing-ritual 1.0.0→1.2.0
- репо нёс гибрид ae45a51 (1.1.0, следы 'карв-аут лиза'); установленные (деплой, результат #1040) чище: claim/лиз выпилены, owner=персистентный assignee, живность из session владельца
- dist/*.skill пересобраны (build.ps1); установленные уже были в этом состоянии — репо стал источником правды, совпадающим с деплоем
- сверка: claim_next/claim_expires/task_heartbeat/admin_release_lease — 0 вхождений в установленных mappa-* (подтверждено и на этом хосте)
2026-08-25 01:04:12 +03:00
ae45a51420 feat(skills): интерактивный контракт (wiki:2660) — выпил claim/TTL/heartbeat из mappa-* скилов (#1040)
- mappa-task-work 1.0.0→1.1.0: «взять таску» = task_update(status=active, owner=<сессия>, version) + 409-retry; release = status=ready; close с version; heartbeat убран (живость из session live-ingest); MCP-таблица и loop-mode обновлены
- mappa-knowledge 1.0.0→1.1.0: wiki_create карв-аут, wiki_update version+409; лиз-секция убрана
- mappa-delegation 1.0.0→1.1.0: task_create карв-аут, close/update version+409
- mappa-brainstorm-promote 1.2.0→1.3.0: create карв-аут, 422 busy → 409-семантика
- mappa-messaging 1.0.0→1.1.0: task_create/close карв-аут + version+409
- mappa-closing-ritual: task_close version+409 (упоминания)

Откат claim-механики из скилов; контракт = wiki:2660.
2026-08-25 00:27:25 +03:00
aa80e9faa5 chore(hermes/readme): cleanup after mappa-skill-suite — mapping.yaml: drop 10 stale entries (deleted skills), add 7 mappa-* as pending; dist-hermes orphans + SKIPPED.md stale lines removed; README install examples → current skills [skip-tdd: visual] 2026-08-24 23:05:01 +03:00
2115e2cd50 meta(tasks): close [mappa-skill-suite-review] in OpeItcLoc03/skills 2026-08-24 20:01:14 +00:00
44ac3be5b7 meta(tasks): #1065 review record — approve-with-findings, all fixed 2026-08-24 23:01:03 +03:00
a7144f6523 fix(mappa-task-work): review finding — review-umbrella attribution precise (delegation for impl, promote for promotions) [skip-tdd: visual] 2026-08-24 23:01:03 +03:00
3c311427c8 fix(mappa-suite): review findings — promote: cycle/procedure framing (suite key decision 1); messaging: EN triggers added [skip-tdd: visual] 2026-08-24 23:01:03 +03:00
422fb84664 meta(tasks): update [mappa-skill-suite-review] in OpeItcLoc03/skills 2026-08-24 19:52:48 +00:00
60f317ace0 feat(mappa-session-orient): new skill v1.0.0 — start-phase ritual (contract→pull→handoff-read→inbox-raise→liveness→live-ingest query); absorbs pulling-before-work/session-handoff(read)/session-inbox-monitor/using-system-snapshot; 404-skip for undeployed /session [skip-tdd: visual] 2026-08-24 22:52:30 +03:00
3dff74d584 meta(tasks): close [mappa-session-orient] in OpeItcLoc03/skills 2026-08-24 19:52:27 +00:00
1f29e60b51 feat(mappa-closing-ritual): new skill v1.0.0 — finish-phase (handoff write + PROPOSE wiki/task closes, confirm-gated, mode=light for ad-hoc); absorbs session-handoff write-part [skip-tdd: visual] 2026-08-24 22:50:28 +03:00
9bddab1836 meta(tasks): close [mappa-closing-ritual] in OpeItcLoc03/skills 2026-08-24 19:50:25 +00:00
0efd8cd814 meta(tasks): update [mappa-closing-ritual] in OpeItcLoc03/skills 2026-08-24 19:49:21 +00:00
525a10048b feat(mappa-task-work): merge using-tasks + task-format + task-loop + priority-due → mappa-task-work v1.0.0 (central cycle, loop-mode inside, priority/due section, old names = trigger synonyms) [skip-tdd: visual] 2026-08-24 22:49:08 +03:00
6d087f96a2 meta(tasks): close [mappa-task-work] in OpeItcLoc03/skills 2026-08-24 19:49:06 +00:00
cbd12fb3bc meta(tasks): update [mappa-task-work] in OpeItcLoc03/skills 2026-08-24 19:47:40 +00:00
0d8bda1714 feat(mappa-delegation): rewrite delegate-task → mappa-delegation v1.0.0 (cycle pre-flight→letter→review-umbrella, suite refs, #1054 note, old name = trigger synonym) [skip-tdd: visual] 2026-08-24 22:47:26 +03:00
9c7d256fe5 meta(tasks): close [mappa-delegation] in OpeItcLoc03/skills 2026-08-24 19:47:24 +00:00
62ec047241 meta(tasks): update [mappa-delegation] in OpeItcLoc03/skills 2026-08-24 19:46:13 +00:00
c688a60b2a feat(mappa-brainstorm-promote): UPDATE workshop-promote-brainstorm v1.1.0→1.2.0 — mappa-service channel (fold-in 1: lease, wiki_create, task_create sequential, no pointers if spec in wiki, service review-umbrella, covering letter); old name = trigger synonym [skip-tdd: visual] 2026-08-24 22:46:01 +03:00
bf6d529ea2 meta(tasks): close [mappa-brainstorm-promote] in OpeItcLoc03/skills 2026-08-24 19:45:58 +00:00
2cd12ae321 meta(tasks): update [mappa-brainstorm-promote] in OpeItcLoc03/skills 2026-08-24 19:43:06 +00:00
bc7b00fa21 chore(dist): rebuild mappa-knowledge.skill (drop using-wiki*.skill) 2026-08-24 22:42:54 +03:00
b9c13a0aaf feat(mappa-knowledge): merge using-wiki + using-wiki-graph → mappa-knowledge v1.0.0 (cycle ingest/query/lint + graph layer, guarded failure-mode, old names = trigger synonyms) [skip-tdd: visual] 2026-08-24 22:42:54 +03:00
fe8484bb2b meta(tasks): close [mappa-knowledge] in OpeItcLoc03/skills 2026-08-24 19:42:52 +00:00
37ecc1f8e5 meta(tasks): update [mappa-knowledge] in OpeItcLoc03/skills 2026-08-24 19:40:58 +00:00
437cc85e30 chore(dist): rebuild mappa-messaging.skill (drop inter-session-messaging.skill) 2026-08-24 22:40:38 +03:00
74c407dc73 feat(mappa-messaging): rewrite inter-session-messaging → mappa-messaging v1.0.0 (cycle SEND/RECEIVE/POLICY, suite naming, old name = trigger synonym); absorb old skill [skip-tdd: visual] 2026-08-24 22:40:37 +03:00
e2077ec062 meta(tasks): close [mappa-messaging] in OpeItcLoc03/skills 2026-08-24 19:40:22 +00:00
b5024703f8 meta(tasks): update [mappa-messaging] in OpeItcLoc03/skills 2026-08-24 19:37:37 +00:00
0c97ed973a docs(skills): конвенция реф-формата (#1028) в messaging/knowledge — полные имена task:/wiki:/inbox:, слаг-first, wiki:NNNN единый; using-wiki: схема AGENTS (canon) + CLAUDE (pointer) (#1032); [skip-tdd: visual] 2026-08-24 22:27:51 +03:00
1e3fa36d4c chore(dist): rebuild от текущих исходников — отложенный артефакт #983-батча 2026-08-24 22:27:51 +03:00
2378889300 meta(tasks): update [mappa-skill-suite-review] in OpeItcLoc03/skills 2026-08-24 19:22:48 +00:00
78e4779514 meta(tasks): update [mappa-brainstorm-promote] in OpeItcLoc03/skills 2026-08-24 19:17:54 +00:00
930f3f6fad meta(tasks): create .tasks/2026-08-24-01065-mappa-skill-suite-review.md in OpeItcLoc03/skills 2026-08-24 18:49:38 +00:00
9eaa01eba2 meta(tasks): create [mappa-skill-suite-review] in OpeItcLoc03/skills 2026-08-24 18:49:37 +00:00
fa9a34716c meta(tasks): create .tasks/2026-08-24-01064-mappa-session-orient.md in OpeItcLoc03/skills 2026-08-24 18:49:28 +00:00
fe24b1b19d meta(tasks): create [mappa-session-orient] in OpeItcLoc03/skills 2026-08-24 18:49:27 +00:00
d42a28a67d meta(tasks): create .tasks/2026-08-24-01063-mappa-closing-ritual.md in OpeItcLoc03/skills 2026-08-24 18:49:21 +00:00
0dc12d67b0 meta(tasks): create [mappa-closing-ritual] in OpeItcLoc03/skills 2026-08-24 18:49:21 +00:00
ce96cf7cc0 meta(tasks): create .tasks/2026-08-24-01062-mappa-task-work.md in OpeItcLoc03/skills 2026-08-24 18:49:15 +00:00
5fd7ed7b77 meta(tasks): create [mappa-task-work] in OpeItcLoc03/skills 2026-08-24 18:49:15 +00:00
182902177b meta(tasks): create .tasks/2026-08-24-01061-mappa-delegation.md in OpeItcLoc03/skills 2026-08-24 18:49:10 +00:00
954833f910 meta(tasks): create [mappa-delegation] in OpeItcLoc03/skills 2026-08-24 18:49:09 +00:00
6e7f5ac5d4 meta(tasks): create .tasks/2026-08-24-01060-mappa-brainstorm-promote.md in OpeItcLoc03/skills 2026-08-24 18:49:04 +00:00
6b705989d9 meta(tasks): create [mappa-brainstorm-promote] in OpeItcLoc03/skills 2026-08-24 18:49:04 +00:00
d8a18401a7 meta(tasks): create .tasks/2026-08-24-01059-mappa-knowledge.md in OpeItcLoc03/skills 2026-08-24 18:48:57 +00:00
be39b92117 meta(tasks): create [mappa-knowledge] in OpeItcLoc03/skills 2026-08-24 18:48:57 +00:00
ec22eaf9f3 meta(tasks): create .tasks/2026-08-24-01058-mappa-messaging.md in OpeItcLoc03/skills 2026-08-24 18:48:47 +00:00
8fec86032e meta(tasks): create [mappa-messaging] in OpeItcLoc03/skills 2026-08-24 18:48:47 +00:00
8b0fd954ee feat(skills): report-mappa-issue v0.1.0 — temporary mappa deviation reporting (TDD: RED swallowed 500s/locally-logged, GREEN mails mappa+.workshop) 2026-08-24 19:53:48 +03:00
7741b9a0c8 meta(tasks): close #1047 task-priority-due-task-format-skill 2026-08-24 18:59:23 +03:00
bc0bdb78d1 docs(task-format): v0.4.0 — Priority/Due поля (task-priority-due, #1047): задаются только при создании, агентский update отклоняется; сортировка claim_next, overdue-scan 2026-08-24 18:53:18 +03:00
c0ad1cd5a6 meta(tasks): create .tasks/2026-08-24-01047-task-priority-due-task-format-skill.md in OpeItcLoc03/skills 2026-08-24 15:21:48 +00:00
01e0b77505 meta(tasks): create [task-priority-due-task-format-skill] in OpeItcLoc03/skills 2026-08-24 15:21:48 +00:00
46724e2c88 fix(using-wiki): v2.1.0 — оп-лог автоматический (таблица logs, ратификация 2026-08-24), log-страница и ручной каталог убраны; каталог = entity_search (#983) 2026-08-24 17:48:01 +03:00
c53ed66ba5 fix(skills): repatriate workshop-promote-brainstorm source (was orphan, only in ~/.agents/skills); session-health v0.1.1 — handoff is mappa entity, not .tasks/NEXT_SESSION.md (#983) 2026-08-24 17:19:28 +03:00
95 changed files with 1570 additions and 4974 deletions

5
.agents/inbox/README.md Normal file
View File

@@ -0,0 +1,5 @@
# ⛔ Файловый инбокс закрыт
**Не читать. Не править.** Канал почты — mappa (`mcp__mappa__inbox_*`): письма = inbox-сущности проекта. Скилы: `mappa-messaging`, `mappa-session-orient` (raise on start).
Файлы ниже — легаси-история (файловый канал закрыт решением 2026-08-25).

3
.gitignore vendored
View File

@@ -90,3 +90,6 @@ coverage/
# Missing here made `git status` see `?? .tasks/claims/` → poller skipped every # Missing here made `git status` see `?? .tasks/claims/` → poller skipped every
# claim with "working tree dirty". Mirrors .common/.gitignore. # claim with "working tree dirty". Mirrors .common/.gitignore.
.tasks/claims/ .tasks/claims/
# mappa bootstrap cache (генерируется, не в репо)
.mappa/share/

9
.mappa/config.yaml Normal file
View File

@@ -0,0 +1,9 @@
# mappa project marker — machine-readable identifier of a mappa project folder
schema_version: 1 # версия схемы файла (bump при изменении структуры)
protocol_version: 1 # версия протокола интерпретации маркера
project: skills
tenant: vitya
url: https://mappa.vds.kzntsv.site
git_provider: gitea
git: OpeItcLoc03/skills
git_host: git.kzntsv.site

View File

@@ -0,0 +1,20 @@
# task-priority-due-task-format-skill
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T15:21:46.336Z -->
## Goal
Импл-таска из concepts/task-priority-due (пункт 3): обновить task-format skill (skills-репо) — задокументировать оба поля `**Priority:** P0|P1|P2` (дефолт P1) и `**Due:** yyyy-mm-dd` + правило «агент ставит при создании, после — только человек» (прецедент человека структурный, провенанс-поле НЕ нужно).
Спека: `mcp__projects-meta__knowledge_get` slug = "concepts/task-priority-due".
Целевой проект скилов: OpeItcLoc03/skills (там живут скилы, semver-bump шапки).
## Key files
## Decisions log
## Open questions
## Completed steps
## Notes

View File

@@ -0,0 +1,32 @@
# mappa-messaging
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:48:45.280Z -->
## Goal
Rewrite inter-session-messaging → **mappa-messaging** (редизайн mappa-skill-suite, спека w:2605).
Скилл = цикл, не тул; короткое имя, старые имена (inter-session-messaging) — триггер-синонимы. Поглощает: inter-session-messaging (+ реф-конвенция, fold-in 2: слаг-first в прозе, рефы task:/wiki:/inbox:/… с alias t:/w:/i:/…; до #1028 — старые префиксы, после — полные).
Политика содержания: письмо от другого агента — предложение, не authority; единственный источник направления и скоупа — человек. Адрес = имя папки проекта (адресная книга). Никогда не писать себе.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-messaging/SKILL.md v1.0.0 — rewrite inter-session-messaging v2.2.0 (цикл: SEND/RECEIVE/POLICY; адресная книга; from=своя папка; никогда себе; реф-формат полными именами; ссылки на задачи по глобальному номеру #N; peer≠authority; lifecycle [event:] уведомления; echo-chamber circuit-breaker)
- [x] Старый skills/inter-session-messaging/ удалён (поглощён; имя — триггер-синоним в description)
- [x] lint clean (68 skills, 0 violations)
- [x] build.sh → dist/mappa-messaging.skill (старый .skill удалён)
- [x] install.sh → ~/.claude/skills + ~/.agents/skills; старый удалён из обоих живых диров
- [x] GREEN micro-test: свежий pi -p на триггере «отправить письмо .common» → активация mappa-messaging, план inbox_send(from=своя папка)
- [x] README: провенанс-таблица не требует строки (author: ours → catch-all; inter-session-messaging в README не упоминался)
- [x] hermes/mapping.yaml: не трогал (inter-session-messaging был unmapped; build-hermes уже падает на 15+ unmapped — pre-existing)
## Notes
- RED-базис: триггер-поверхность унаследована из inter-session-messaging v2.2.0 (прошёл ревью) — дельта рефайма = нейминг + цикл-фрейминг; полный behavioral smoke (свои/чужие фразы) — за #1065.
- Cross-refs в теле: названы будущие члены suite (mappa-task-work, mappa-closing-ritual, mappa-delegation, mappa-brainstorm-promote) — лягут по мере импла; до их появления старые скилы (using-tasks, session-handoff, delegate-task) продолжают существовать.

View File

@@ -0,0 +1,30 @@
# mappa-knowledge
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:48:55.340Z -->
## Goal
Rewrite using-wiki + using-wiki-graph → **mappa-knowledge** (редизайн mappa-skill-suite, спека w:2605).
Скилл = цикл, не тул; старые имена — триггер-синонимы. Поглощает: using-wiki, using-wiki-graph (+ реф-конвенция, fold-in 2). Писать НЕЙТРАЛЬНО — не зависеть от summaries (таски #1026 нет); реф-префиксы до апгрейда #1028 — старые (w:/t:/i:), после — полные.
Relational/структурные вопросы (связи, backlinks, сироты) — через graph-тулы, guarded failure-mode: одна страница и стоп, без многохоповых цепочек сам.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-knowledge/SKILL.md v1.0.0 — слияние using-wiki v2.2.0 + using-wiki-graph v1.1.0 в один цикл-скил (ingest/query/lint + граф-слой для реляционных/структурных вопросов)
- [x] Старые skills/using-wiki/ + skills/using-wiki-graph/ удалены (поглощены; имена — триггер-синонимы в description)
- [x] lint clean (67 skills, 0 violations)
- [x] build.sh → dist/mappa-knowledge.skill; install.sh → dual targets; старые удалены из живых диров
- [x] GREEN micro-test: свежий pi -p на реляционном вопросе (связь таска↔спека) → активация mappa-knowledge, граф-слой (graph_path→no-path, backlinks), корректная семантика рёбер
- [x] Писано нейтрально (summaries/#1026 не упоминается); реф-конвенция полными именами (#1028, уже была в исходниках)
## Notes
- RED-базис: триггер-поверхность унаследована из using-wiki/using-wiki-graph (прошли ревью); дельта = слияние + цикл-фрейминг + guarded failure-mode графа. Полный behavioral smoke — за #1065.
- Побочная lint-находка GREEN-теста: рефы в прозе (не [[викилинки]]) рёбер не дают → спека может быть сиротой, «таска↔спека» в графе теряется. Это известная семантика решения 4 (рёбра только из [[refs]]), не баг скила — отмечено как наблюдение, кандидат в follow-up, если понадобится проставлять [[викилинки]] при создании тасок-промоушена.

View File

@@ -0,0 +1,28 @@
# mappa-brainstorm-promote
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:01.966Z -->
## Goal
UPDATE workshop-promote-brainstorm → **mappa-brainstorm-promote** (редизайн mappa-skill-suite, спека w:2605). АПДЕЙТ, не rewrite.
Fold-in 1: mappa-service target. Промоут в mappa-сервисные борды (mappa, .common, …) — отдельный канал: сервисные тулы mcp__mappa__task_create/wiki_create (под лизом, claim через task_claim_next); pointers-таска НЕ нужна, если спека уже в вики проекта (w:NNNN) — описание импл-таски ссылается на неё; review-umbrella — сервисная таска (status=blocked, blocker=impl#); covering-письмо в инбокс цели (канон delegate-task) — в обоих каналах. Файловый путь (projects-meta → .tasks/STATUS.md) остаётся.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-brainstorm-promote/SKILL.md v1.2.0 (MINOR) — UPDATE workshop-promote-brainstorm: добавлена 4-я ветка маршрутизации **mappa-service** (fold-in 1: лиз через task_claim_next, спека через mcp__mappa__wiki_create, импл-таски через mcp__mappa__task_create, pointers-таска НЕ нужна если спека в вики w:NNNN, review-umbrella сервисная таска, covering-письмо в инбокс цели)
- [x] NB (2026-08-24, инцидент): tasks_create ПОСЛЕДОВАТЕЛЬНО, не батчем (гонка sha-CAS счётчика agenda; при промоуте mappa-skill-suite 6/7 упали) — в шаге 8 + failure modes + what-not-to-do
- [x] File channel (projects-meta → .tasks/STATUS.md) сохранён; шаги перенумерованы (вставлен шаг 4)
- [x] Старое имя workshop-promote-brainstorm — триггер-синоним в description; каталог git mv
- [x] lint clean (67 skills, 0 violations); build.sh → dist/mappa-brainstorm-promote.skill (старый .skill удалён); install.sh → dual; старый удалён из живых диров
- [x] GREEN micro-test: свежий pi -p на «промоутни брейнсторм… таргет mappa» → активация mappa-brainstorm-promote, service channel (лиз/task_create последовательно/wiki_create/без pointers/review-umbrella/covering-письмо)
## Notes
- RED-базис: UPDATE существующего скила (триггеры не менялись); дельта = fold-in 1 + NB последовательности. Полный behavioral smoke — за #1065.
- Актуальность шага 3 (определение канала): сервисные борды — mappa, .common (доска в mappa-сущностях); обычные проекты — файловая доска. Определение по наличию .tasks/STATUS.md.

View File

@@ -0,0 +1,29 @@
# mappa-delegation
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:07.632Z -->
## Goal
Rewrite delegate-task → **mappa-delegation** (редизайн mappa-skill-suite, спека w:2605).
Скилл = цикл, не тул; старые имена — триггер-синонимы. Поглощает: delegate-task. Каждая кросс-проектная делегация — пара: tasks_create + covering-письмо в инбокс получателя (таска на доске не пингует живую сессию). #1054 create-без-лиза — опционально (контракт работает на текущих тулах); перейти, когда #1054 имплементится.
НЕ применимо: self-assigned таски на своей доске («создать задачу себе» → mappa-task-work), работа своими руками, workshop-внутренние таски.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-delegation/SKILL.md v1.0.0 — rewrite delegate-task v0.5.1 (цикл: pre-flight gate → шаблон → preview → confirm → covering-письмо → review-umbrella → downstream)
- [x] Старый skills/delegate-task/ удалён (поглощён; имя — триггер-синоним в description)
- [x] Suite-ссылки: using-tasks→mappa-task-work, inter-session-messaging→mappa-messaging, using-wiki→mappa-knowledge; нота лизинговой модели #1054 (create-без-лиза — опционально, контракт работает на текущих тулах)
- [x] lint clean (67 skills, 0 violations); build.sh → dist/mappa-delegation.skill (старый .skill удалён); install.sh → dual; старый удалён из живых диров
- [x] GREEN micro-test: свежий pi -p на «создать задачу на агента… common» → активация mappa-delegation, обязательная пара tasks_create + covering-письмо (адрес из адресной книги, [event: created]), review-umbrella с наследованием weight
## Notes
- RED-базис: тело унаследовано из delegate-task v0.5.1 (прошёл ревью + smoke); дельта = rename, suite-ссылки, цикл-фрейминг, нота #1054. Полный behavioral smoke — за #1065.
- Поглощает delegate-task без потери контента (все шаги 1–7 сохранены, включая weight-наследование review и downstream-правило task+letter).

View File

@@ -0,0 +1,31 @@
# mappa-task-work
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:13.376Z -->
## Goal
Rewrite using-tasks + task-format + task-loop + priority-due → **mappa-task-work** (редизайн mappa-skill-suite, спека w:2605). Центральный, крупный.
Скилл = цикл, не тул; старые имена — триггер-синонимы. Поглощает: using-tasks, task-format (вливается), task-loop (loop-mode ВНУТРИ, вариант A — отдельный скилл не создаётся), priority-due-раздел (P0-P2 + дедлайны: приоритет = территория человека, агенты ставят только при создании; дефолт P1; дедлайн-механика: notify при просрочке без авто-бампа).
Цикл: выбор работы (claim) → исполнение → сдача (close + review-umbrella). Один триггер-сёрфейс: «поработай очередь» / «work the queue» → mode=loop.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-task-work/SKILL.md v1.0.0 — центральный цикл: ориентация → выбор работы (claim, priority/due) → исполнение → сдача (close + review-umbrella) + пауза/переключение
- [x] Loop-mode ВНУТРИ (вариант A, отдельный скил не создаётся): «поработай очередь»/«work the queue» → цикл claim→work→close→claim; пустая очередь = стоп, без демона/CronCreate; session_break gate; consult gate (human-only/strict-human → STOP перед close/commit)
- [x] Priority/Due-раздел: приоритет = территория человека, агент ставит только при создании, дефолт P1, просрочка → admin_overdue_scan notify однократно, без авто-бампа
- [x] Формат таски (из task-format): mappa task_create схема (priority/due при создании) + legacy STATUS.md блок (переходный, Weight/Notify обязательны)
- [x] Поглощены: using-tasks (борд/лиз/close/notify/рефы [[task:N]]), task-format (формат), task-loop (loop-mode), task-priority-due (раздел). Старые имена — триггер-синонимы в description
- [x] lint clean (65 skills, 0 violations); build.sh → dist/mappa-task-work.skill (старые .skill удалены); install.sh → dual; старые удалены из живых диров
- [x] GREEN micro-test: свежий pi -p на «поработай очередь» → активация mappa-task-work, loop-mode, стоп-гейты, пустая очередь = стоп без поллинга
## Notes
- RED-базис: контент унаследован из трёх скилов (все прошли ревью/smoke); дельта = слияние + цикл-фрейминг + priority/due раздел. Полный behavioral smoke (вкл. loop-mode, session-break, empty-stop) — за #1065.
- Убраны: task-loop ссылки на projects-meta claim (primary — mappa task_claim_next; file channel — переходный, описан в секции legacy).

View File

@@ -0,0 +1,30 @@
# mappa-closing-ritual
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:19.363Z -->
## Goal
НОВЫЙ скилл **mappa-closing-ritual** (редизайн mappa-skill-suite, спека w:2605).
Финиш-фаза форкфлоу: session-handoff(write) + PROPOSE wiki-ingest + task closes + sweep. Старт ≠ финиш: closing-ritual = write-path с процедурой и подтверждением. Ad-hoc: mode=light — явный вопрос «Сделать handoff?» в конце сессии (НЕ автоматический sweep); решение за человеком. Поглощает: session-handoff(write-часть).
Handoff: sliding, per-project, versioned-история; read на старте — mappa-session-orient, write на финише — тут. Мутации (handoff write / wiki-ingest / task closes) — только после подтверждения пользователя.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-closing-ritual/SKILL.md v1.0.0 — НОВЫЙ скилл (финиш-фаза): scope check → mid-task capture → compose handoff → handoff_write (версия h:N) → PROPOSE wiki-ingest → PROPOSE task closes → один блок-предложение; мутации только после «да»
- [x] mode=light для ad-hoc: явный вопрос «Сделать handoff?», НЕ автоматический sweep; решение за человеком
- [x] Поглощает session-handoff (write-часть); read-часть уходит в mappa-session-orient (#1064); старое имя — триггер-синоним
- [x] Старый skills/session-handoff/ удалён (включая hooks/commit-detector — новый дизайн: ритуал на session-end, не на substantive commit)
- [x] lint clean (65 skills, 0 violations); build.sh → dist/mappa-closing-ritual.skill; install.sh → dual; старый удалён из живых диров
- [x] GREEN micro-test: свежий pi -p на «завершаем сессию» → активация mappa-closing-ritual, полный ритуал (7 шагов), мутации только после «да», mode=light «Сделать handoff?»
## Notes
- RED-базис: write-процедура унаследована из session-handoff v1.0.0 (прошёл ревью); дельта = split read/write + mode=light + confirm-гейт. Полный behavioral smoke (триггеры свои + false-positive на task-зоне) — за #1065.
- commit-detector hooks удалены осознанно: suite проектирует closing-ritual как session-end-driven, а не commit-driven.

View File

@@ -0,0 +1,31 @@
# mappa-session-orient
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:25.792Z -->
## Goal
НОВЫЙ скилл **mappa-session-orient** (редизайн mappa-skill-suite, спека w:2605). Самый новый, делается ПОСЛЕДНИМ.
Старт-фаза форкфлоу: контракт + чтение (нужен и для ad-hoc, где нет AGENTS.md-контракта). Поглощает: pulling-before-work (полный цикл --ff-only), session-handoff(read), session-inbox-monitor(raise), using-system-snapshot (liveness-сводка «живо/мертво», одна строка), live-ingest query (потребитель session-live-ingest: GET /session?project=, stale-active детект, «другая связка + не завершена» → предложение: забить / дернуть письмом / продолжить).
Граница: session-orient = «живо/мертво»; глубокая диагностика — вне suite (адхок). Эскалация: проблема на старте → не углубляться, передать человеку/диагностической сессии.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] skills/mappa-session-orient/SKILL.md v1.0.0 — старт-фаза: контракт → pull (--ff-only, полный цикл) → handoff read (staleness >7д → ask; orient+ask, без auto-execute) → inbox raise+sweep → liveness-сводка (meta_health/admin_status/snapshot, «живо/мертво») → live-ingest query (session_list, stale-active краш-детект, «другая связка → предложить»)
- [x] Граница orient/ops (w:2605 round 3): «живо/мертво»; проблема на старте → эскалация человеку/диагностической сессии, не углубление
- [x] Поглощены: pulling-before-work, session-handoff(read), session-inbox-monitor(raise), using-system-snapshot (liveness); старые имена — триггер-синонимы
- [x] Live-ingest 404-skip задокументирован (роуты /session не задеплоены — сервер #1022 в репо, деплой ждёт #1055); контракт — w:2604
- [x] mappa-messaging: ссылки session-inbox-monitor → mappa-session-orient (inbox raise) обновлены (3 места)
- [x] lint clean (63 skills, 0 violations); build.sh → dist/mappa-session-orient.skill; install.sh → dual; поглощённые удалены из живых диров
- [x] GREEN micro-test: свежий pi -p на «начало сессии» → ритуал по шагам (контракт→pull→handoff→inbox→liveness→live-ingest), граница «живо/мертво» + эскалация, 404-skip, read-only
## Notes
- #1064 была 🔵 blocked ← #1024 (клиент session-sync). Скил-документ завершён по контракту w:2604/w:2605; live-ingest E2E (шаг 6) отложен: сервер #1022 не задеплоен (#1055), клиент #1024 (.common) открыт. 404-skip в скиле — ориентация не блокируется.
- RED-базис: контент унаследован из 4 поглощённых скилов (все прошли ревью); дельта = слияние + live-ingest query + граница orient/ops. Полный behavioral smoke — за #1065.

View File

@@ -0,0 +1,49 @@
# mappa-skill-suite-review
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-24T18:49:35.610Z -->
## Goal
Skill-review checkpoint для mappa-skill-suite (промоушен 2026-08-24).
**Спецификация:** w:2605 concepts/mappa-skill-suite (mappa wiki). **Источник дизайна (trace):** .workshop/.archive/2026-08-24-mappa-skill-suite.md.
**Импл-таски:** #1058 mappa-messaging, #1059 mappa-knowledge, #1060 mappa-brainstorm-promote, #1061 mappa-delegation, #1062 mappa-task-work, #1063 mappa-closing-ritual, #1064 mappa-session-orient.
**Кто делает:** **не имплементер.** Другая сессия / другой день / другой агент (identity-not-location).
**Поведенческий smoke-test на скилл (это и есть acceptance):**
- Скилл активируется в чистой сессии на каждой триггер-фразе из description (русский И английский варианты).
- Скилл **не** активируется на 2-3 близких но не своих фразах из соседних доменов (false-positive check).
- Каждый шаг секции Steps отрабатывает на тестовом буфере без ошибок.
- Failure modes уводят в abort, не в частичный успех.
- What NOT to do соответствует реальности.
**Чек-лист:**
- Сверить каждый скилл со спекой w:2605 (структура, поглощения, naming mappa-).
- Старые имена работают как триггер-синонимы (inter-session-messaging, using-wiki, delegate-task, workshop-promote-brainstorm, using-tasks, session-handoff, pulling-before-work…).
- mappa-session-orient сделан ПОСЛЕДНИМ и учитывает live-ingest (#1022/#1024).
- mappa-task-work: loop-mode, priority/due-раздел, session-break.
Findings → follow-up tasks через tasks_create в OpeItcLoc03/skills.
**Закрытие:** только когда все findings зафайлены ИЛИ ревьюер подтвердил «нет findings» в close-note.
## Key files
## Decisions log
## Open questions
## Completed steps
- [x] Ревью запущено через clean-context субагентов (не-имплементер identity: review_subagent с чистой спецификацией + свежие pi -p сессии без истории) — метод review-kit-pi-method
- [x] **Структурное ревью vs w:2605 — 7/7:** batch 1 (messaging/knowledge/promote/delegation): 3 PASS, promote NEEDS-WORK → исправлено (cycle/procedure фрейминг, фикс 78542c0); batch 2 (task-work/closing-ritual/session-orient): 3 PASS
- [x] **Минорные findings исправлены:** EN-триггеры в messaging (78542c0), attribution review-umbrella в task-work (45baadc); остальные миноры — стилистические (inline-absorption vs таблица), не блокеры
- [x] **Behavioral smoke (свежие pi -p, чистая сессия):**
- Позитив (старые имена = синонимы): using-tasks → mappa-task-work, using-wiki → mappa-knowledge, delegate-task → mappa-delegation, «напиши письмо» → mappa-messaging, «промоутни… таргет mappa» → mappa-brainstorm-promote (service channel), «завершаем сессию» → mappa-closing-ritual, «начало сессии» → mappa-session-orient, «поработай очередь» → loop-mode
- Негатив: «поставь таску себе» → НЕ делегирование (mappa-task-work территория), «отбой» → анти-триггер, без активации
- [x] **Отложенные зависимости (не findings):** live-ingest E2E (шаг 6 session-orient) — после деплоя #1055 + клиента #1024 (404-skip задокументирован в скиле); build-hermes unmapped — pre-existing
## Notes
- Ревьюер-identity: .workshop (решение оператора) через clean-context субагентов — identity-not-location, имплементерская сессия не оценивала свои артефакты сама.
- Verdict: APPROVE-WITH-FINDINGS → все findings зафайлены и исправлены (3 фикса), блокеров нет.

View File

@@ -0,0 +1,25 @@
# mappa-brainstorm-promote-storm-channel
<!-- created-by: OpeItcLoc03@DESKTOP-NSEF0UK / from: OpeItcLoc03/workshop / 2026-08-25T06:00:37.319Z -->
## Goal
Апдейт скила mappa-brainstorm-promote (1.5.0 → 1.6.0): миграция с файлового канала на mappa storm-сущности.
Скоуп:
1. Буфер шторма = mappa storm-сущность (type=storm) в ЛЮБОМ проекте (не файл .workshop/.brainstorm/). Скил становится project-agnostic: шторм живёт там, где его ведут, не только в воркшопе.
2. Промоут mappa-service маршрута через storm_promote (атомарно buffer → wiki-страница + archive, решение 7), не через git mv в .workshop/.archive/.
3. Зафиксировать «штормы в любом проекте» в mappa-спеке (concepts/mappa) — сейчас скил воркшоп-центричный.
4. Workshop-meta маршрут: файловые .brainstorm/.archive остаются только для локальной методологии зоны — или мигрируют тоже (решить в таске).
5. Summary-дисциплина уже в 1.5.0 (9b606f7) — не дублировать.
Контекст: решение оператора 2026-08-25 («штормы могут вестись не только в воркшопе»). Связано: wiki:2661 (unified search — storm-карточки), task:1048 (review mappa-wiki-search). Исполнитель — workshop-сессия (оператор: «ты сам сделаешь в новой сессии»).
## Key files
## Decisions log
## Open questions
## Completed steps
## Notes

View File

@@ -1,46 +1,3 @@
--- # ⛔ Файловая доска закрыта
_last_updated_: 2026-08-12T17:21:33Z
session_id: 2026-08-12-setup-tasks-noop
---
# Next session handoff **Не читать. Не править.** Канон — mappa (`mcp__mappa__task_*`): task-сущности проекта. Скил: `mappa-task-work`.
**Сессия (headless): «настрой таски» → сработал `setup-tasks` → mode **noop**: доска уже каноническая (STATUS.md 70KB, emoji-легенда, `**Poller:** eligible`, 24 per-task файла, 12 блоков задач). Коммитов нет, мутаций нет. Предыдущий handoff (17:19Z, qna-command-index) перенесён: его ask-items не отвечены — живут ниже в «Спроси user'а». Актуальный снимок доски: 0 🔴 / 3 🟡 / 1 🔵 / 12 ⚪ / 11 🟢.**
## Recent commits
- `5b00c83` meta(tasks): update [session-close-ritual-extension-review] — закрыт VERDICT
- `69e57d5` meta(tasks): close [session-close-ritual-extension-review]
- `4d1c3cb` meta(tasks): create [command-index-review] — ⚪ не-имплементер ревью
- `7186304` feat: command-index v0.1.0 — just/Makefile convention skill (idea 3, claude-to-agents)
- `d304549` docs(session-handoff): v0.5.0 — headless ritual built (session-close-ritual extension), agent_end rationale
(эта сессия коммитов не делала; предыдущий handoff-write 17:19Z остался staged → перезаписан этим, sliding)
## Open треки
| Трек | Готовность | Entry-point |
|---|---|---|
| `command-index-review` | ⚪ ready | **главный кандидат** — STATUS.md. Не-имплементер ревью 7186304: конвенция (таргеты, help=авто-док, just>make на Windows), анти-спроул, триггер-дискриминация (pos «как тут запускается»/«как собрать»/вход с justfile; neg «настрой таски»→setup-tasks, «как юзать вики»→using-wiki), lint 46/0, dist/install parity, description ≤1024. Follow-up вне скоупа: project-bootstrap эмитит justfile. |
| `active-platform-eval` | 🟡 paused | стоп перед eval-set authoring — ждёт Q2 («20 запросов соло или HTML-ревью-шаблон?»). |
| `skill-readmes` | 🟡 paused | англ. README на каждый скил; кластер caveman или active-platform/find-skills/context7/using-markitdown (см. `compress-dedup`). |
| `agent-neutral-skill-pipeline` | 🟡 paused | долг idea 19 п.5 — осознанно отложен. |
| `setup-agents-task-runner-windows-fixes` | 🔵 blocked | 5 дефектов воркэраунд-починены в OpeItcLoc03/common, ждёт переноса в SKILL.md. |
| `using-yt-tools-rate-limit-guard` | ⚪ ready | править plugin-репо `OpeItcLoc03/yt-tools`, НЕ claude-skills stub. |
| `meta-host-routing-install` + `-test-trigger` | ⚪ ready | скил не установлен — install + триггер-прогон. |
| `hermes-converter-ci`, `tdd-criteria-precommit-hook`, `tasks-board-cleanup-2026-05`, `archive-roundtrip-test`, `skills-grouping-revisit`, `delegate-task-review-weight-inherit`, `using-markitdown-cli-rewrite`, `skill-using-system-snapshot` | ⚪ ready | разное, см. STATUS.md блоки. |
## Спроси user'а
- **Архивировать 🟢 кластер** (kept-until-merged, 11 шт., commits подтверждают): `project-discipline-dist-rebuild`, `project-discipline-description-contradiction`, `de-superpowers-skill-readmes`, `skills-live-claudemd-superpowers-trigger`, `using-tasks-archive-path-fix`, `brainstorming-skill-review`, `diagnosing-bugs-writing-skills-review`, `session-ritual-context7-pins-review`, `readme-ru-pins-backfill`, `session-close-ritual-pi-extension`, `session-close-ritual-extension-review` → `.tasks/.archive/done-2026-08.md` (конвенция tasks-board-cleanup). Ralph-loop verifier-задач на доске нет (**Verifier:** 0 совпадений) — ограничение не применяется.
- **Wiki-ingest / докс-фикс (перенос с прошлой сессии, не отвечен)**: README.md врёт про `scripts/install.ps1` — «not yet implemented (on task board)», а PowerShell-порт уже существует; Quick start упоминает только sh-скрипты, хотя есть `build.ps1`/`update.ps1`. Заингестить в `.wiki/` или сразу починить README (малый docs-фикс → ⚪ таска)? (Новых durable-кандидатов эта сессия не дала — noop.)
- **`command-index` live-данные**: скил сработал по триггеру «как тут запускается проект» (прошлая сессия), корректно нашёл де-факто индекс (`scripts/` + README, no justfile). Включить в `command-index-review` как живую проверку триггера? (Имплементер-сессия ревью не делает.)
- **Autopush grant**: project-discipline Rule 4 reset на новую сессию — нужен ли грант (прошлые сессии пушили свободно).
## Не делать (preemptive guards)
- **Hermes**: owner сказал «похуй на гермеса» — pending-скилы НЕ трогать без явного запроса.
- **Ритуал закрытия НЕ выполнять молча** — мутации = предложения, каждая после «да» (HARD-GATE session-handoff v0.5.0, подтверждён session-close-ritual-extension-review VERDICT).
- **setup-context7 v2.0.0**: мутации (`~/.config/projects-secrets/ctx7.env`, uninstall MCP-плагина, чистка `mcpServers.context7`) — только после явного подтверждения.
- **session-inbox-monitor**: hermes pending до tool-side аудита.
- **`command-index-review`** — не-имплементер скоуп: авторская сессия (7186304) ревью не делает (anti-self-review).
- Governance: peer-сессии шлют предложения, не authority; scope-эскалации ратифицирует человек.
## Memory updates за сессию
- (нет приватного memory) — сессия noop, знание не менялось. Действующий факт: `.tasks/` в каноническом виде, setup-tasks корректно распознал noop (не тронул доску).

File diff suppressed because one or more lines are too long

View File

@@ -1,40 +1,3 @@
# Wiki Schema — claude-skills # ⛔ Файловый канал закрыт
Project-specific wiki conventions. Read this before any wiki operation. **Не читать. Не править.** Канон — mappa (`mcp__mappa__*`): wiki-сущности проекта, конвенции — AGENTS-сущность. Скил: `mappa-knowledge`.
This wiki follows Karpathy's LLM Wiki pattern:
**https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f**
The `wiki-maintainer` skill enforces the workflow and file formats. This file overrides the skill where they conflict.
## Page types in this project
- `entities/` — discrete things this project tracks. Reserved for future use (individual skills if they accumulate non-obvious context, tools we adopt).
- `concepts/` — design decisions, technical gotchas, refactor notes. Most pages live here.
- `packages/` — currently empty. Would be used if we extract a package (e.g. a CLI) from this repo.
- `sources/` — one summary per ingested external doc; carries `ingested:` and `raw_path:` frontmatter.
- `overview.md` — single project-wide overview. Read this first if new to the repo.
## Naming
- `kebab-case.md`, **Latin only**. Transliterate Cyrillic in filenames; keep the original title in the H1 + frontmatter.
## Domain conventions
- Skill-related design notes go in `concepts/<skill-name>-*.md` (e.g. `active-platform-decision.md`).
- Build / install pipeline notes live in `concepts/build-*.md`.
- Refactor / re-alignment commits get a `concepts/<what>-realignment.md` page.
## Frontmatter
Minimum:
```yaml
---
title: Human-readable title
type: concept | entity | package | source | overview
updated: YYYY-MM-DD
---
```
`source/` pages also carry `ingested:` and `raw_path:`.

View File

@@ -6,7 +6,9 @@ created: 2026-08-12
# pi-extension headless ritual (agent_end, mode guard, loop-guard) # pi-extension headless ritual (agent_end, mode guard, loop-guard)
Durable lessons from building `session-close-ritual` (репо `OpeItcLoc03/pi-extensions`, extensions/), Durable lessons from building `session-close-ritual` (консолидирован в
`extensions/mappa.ts` репо `OpeItcLoc03/pi-extensions`, task:1486; исторически —
отдельный файл `session-close-ritual.ts`),
the headless injector for the session-handoff closing ritual. All three points the headless injector for the session-handoff closing ritual. All three points
were live-verified, not docs-read-only. were live-verified, not docs-read-only.
@@ -58,6 +60,8 @@ Cache per-cwd; staleness within a long session is accepted (same as
## References ## References
- Source: `~/projects/pi-extensions/extensions/session-close-ritual.ts` (+ `scripts/session-close-ritual.test.mjs`, 12 blocks) - Source: `~/projects/pi-extensions/extensions/mappa.ts` (секция close-ritual;
консолидация 6 расширений, task:1486 — исторически `session-close-ritual.ts`
+ `scripts/session-close-ritual.test.mjs`, 12 blocks, ныне тесты на mappa.ts)
- Skill: `session-handoff` v0.5.0 — «Headless (pi)» section - Skill: `session-handoff` v0.5.0 — «Headless (pi)» section
- pi docs: `extensions.md` — lifecycle diagram, `sendUserMessage` (deliverAs/triggerTurn), mode table - pi docs: `extensions.md` — lifecycle diagram, `sendUserMessage` (deliverAs/triggerTurn), mode table

View File

@@ -1,62 +1,3 @@
# Wiki Index # ⛔ Файловый канал закрыт
Catalog of all wiki pages. One line per page, organized by type. Updated on every ingest / new page.
## Overview
- [overview.md](overview.md) — what claude-skills is, layout, how to navigate
## Entities
<!-- (none yet) -->
## Concepts
- [active-platform-decision.md](concepts/active-platform-decision.md) — why `active-platform` is a skill (not a memory entry); why default = Windows; how it's wired into `project-bootstrap`
- [bootstrap-claude-md-merge.md](concepts/bootstrap-claude-md-merge.md) — project-bootstrap@1.3.0 — Step 5 upgrade path becomes idempotent merge (read → diff vs template → confirm → append missing); fixes silent gap where pre-1.2.0 projects never picked up new canonical triggers (`check across all projects`, `we're on Windows`)
- [bootstrap-skill-deps-check.md](concepts/bootstrap-skill-deps-check.md) — project-bootstrap@1.7.0 — Step 5.6 collapses the per-skill "detect-and-recommend" mirror shape into one generic `trigger → fulfiller` table walker (skill vs plugin kind, never auto-install); subsumes the deferred `[bootstrap-recommend-projects-meta]` and the existing `superpowers`-only detector
- [bootstrap-manifest.md](concepts/bootstrap-manifest.md) — record of which `project-bootstrap` / `setup-wiki` / `setup-tasks` versions initialized this project's `.wiki/` and `.tasks/` layout (overwritten on re-bootstrap; history in git)
- [build-notes.md](concepts/build-notes.md) — why `build.ps1` exists alongside `build.sh`; PS 5.1 backslash-in-zip gotcha; how to extract a `.skill`
- [install-cross-platform.md](concepts/install-cross-platform.md) — paired-script parity contract for `install.{ps1,sh}` AND `build.{ps1,sh}`; rationale for the `--prune` / `-Prune` flag (combined-with-action, global-scan, default-off); install-side prunes target dirs, build-side prunes `dist/*.skill` files
- [install-portability.md](concepts/install-portability.md) — `install.sh` / `build.sh` rewritten to drop `mapfile` (bash 4+) and `find -printf` (GNU only) so stock macOS (bash 3.2 + BSD find) works
- [context7-setup.md](concepts/context7-setup.md) — context7 CLI-first (2026-08-12): `ctx7` CLI + key in `~/.config/projects-secrets/ctx7.env`, plugin `context7@claude-plugins-official` + manual MCP entries removed; setup-context7 skill (one-time install/migrate, confirmation gates) + using-context7 policy; plugin era = rollback reference
- [projects-meta-skills.md](concepts/projects-meta-skills.md) — `setup-projects-meta` + `using-projects-meta` skill pair for the local `projects-meta-mcp` stdio server (cross-project tasks + shared Gitea wiki); local-first rule + two-step mutation pattern
- [project-discipline-design.md](concepts/project-discipline-design.md) — design for project-discipline (four cross-project rules: conventions-over-defaults, master-only, semver-bumping, ask-before-push)
- [pulling-before-work-design.md](concepts/pulling-before-work-design.md) — design for the pulling-before-work skill (mode-3 + skip-on-dirty)
- [repo-layout.md](concepts/repo-layout.md) — flat `skills/`, committed `dist/`, bash + PowerShell scripts; install model
- [skill-versioning.md](concepts/skill-versioning.md) — why infra skills carry `version: <semver>` in frontmatter and how `project-bootstrap` records them in a per-project manifest
- [skill-vs-plugin.md](concepts/skill-vs-plugin.md) — when a bare SKILL.md is enough vs when you actually need a plugin (slash commands, hooks, sub-agents, MCP servers); concrete breakdown of `superpowers`
- [wiki-realignment.md](concepts/wiki-realignment.md) — fixing `project-bootstrap` to create the Karpathy-canonical wiki layout
- [interns-design](concepts/interns-design.md) — interns-design
- [compress-dedup.md](concepts/compress-dedup.md) — `skills/compress/` deleted as a byte-identical dupe of `skills/caveman-compress/`; canonical kept for README + SECURITY + caveman-toolkit branding; better Process-step wording ported across; `version: 1.0.0` added to caveman-compress frontmatter
- [active-platform-eval-design.md](concepts/active-platform-eval-design.md) — spec for eval-driven tuning of `active-platform`: combine the two ⚪ tasks into one workstream, 20-query cross-platform eval set (≥3 per OS + near-miss negatives), `run_loop.py` autoloop **in parallel** with manual body sweep (WSL / BSD / ambiguity), version 1.0.0 → 1.1.0 (MINOR). Status: paused after design + pre-flight check, before eval-set authorship
- [interns-repo-read-design](concepts/interns-repo-read-design.md) — interns-repo-read-design
- [hermes-skills-rollout-design](concepts/hermes-skills-rollout-design.md) — hermes-skills-rollout-design
- [tdd-criteria-design](concepts/tdd-criteria-design.md) — tdd-criteria-design
- [project-bootstrap-meta-isolation.md](concepts/project-bootstrap-meta-isolation.md) — project-bootstrap@1.11.0 — Step 1 ships meta-isolation block in `.gitignore` (`!.claude/`, `!.tasks/`, `!.wiki/`, ...) so own greenfield/upgrade projects re-enable agent meta-paths against global `core.excludesFile` cutter. Marker-based append-only on existing files; smoke-tested with negative control
- [interns-grep-audit-design](concepts/interns-grep-audit-design.md) — interns-grep-audit-design
- [session-handoff-skill-design.md](concepts/session-handoff-skill-design.md) — design rationale for the `session-handoff` skill (sliding overwrite into `.tasks/NEXT_SESSION.md`, phrase whitelist + substantive-commit heuristic, optional PostToolUse hook for harness-side determinism, orient+ask default, project scope, cluster 7/7 closure)
- [using-tasks-session-break.md](concepts/using-tasks-session-break.md) — `using-tasks` v1.2.0 `session_break` marker: task-author-set boolean/string flag; after a task closes 🟢, before `tasks_claim_next`, an autonomous agent prints the verbatim SESSION BOUNDARY line and stops instead of chaining the next task. Absent → unchanged
- [delegate-task-session-break.md](concepts/delegate-task-session-break.md) — `delegate-task` v0.2.2 — authoring side of the `session_break` marker (consumer = [[using-tasks-session-break]]): pre-flight Q6 + optional template field `session_break: true | "<hint>"`; three set-it cases (domain-switch / milestone / heavy infra); not a default
- [delegate-task-review-weight.md](concepts/delegate-task-review-weight.md) — `delegate-task` v0.2.3 — Step 5 review-task now sets explicit `weight`, inherited from impl with a `needs-claude` floor (impl `needs-human`→review `needs-human`; `cheap-ok`→`needs-claude`). Fixes the reconciler skipping weightless review tasks (root cause of manual patch `c0af151`)
- [using-system-snapshot-design.md](concepts/using-system-snapshot-design.md) — `using-system-snapshot` v0.1.0 — thin read-only skill wrapping the single `mcp__projects-meta__meta_system_snapshot` call (poller + local docker + cached task summary); replaces scattered `tasklist`/`docker ps`/manual `meta_status`; core rule = no liveness claim without calling the tool this turn; three-line output; defers deep docker to [[using-vds-ops]] and precise tasks to [[using-projects-meta]]
- [using-tasks-status-archival.md](concepts/using-tasks-status-archival.md) — `using-tasks` v1.3.0 done-task archival rule (≥10 🟢 → `.tasks/archive/YYYY-MM.md`) fixes STATUS.md bloat; documents why `tasks_get_status` (single-task, by slug) / `tasks_aggregate` (cross-project cache) can't replace the orientation board-read, so the literal task instruction was not followed
- [delegate-task-negative-trigger-fp.md](concepts/delegate-task-negative-trigger-fp.md) — `delegate-task` v0.2.1 FP fix: «создать задачу себе» stem-matched the «создать задачу на агента» positive trigger; abstract "does NOT apply when doing the work yourself" carve-out loses to literal stem-match under the 1%-rule → made the negative literal + routed (→ using-tasks). Verified pos 5/5, neg 4/5 (was 0/5)
- [using-markitdown-cli-migration.md](concepts/using-markitdown-cli-migration.md) — `using-markitdown` v1.0.0→v1.0.1 (PATCH): rewrote from the Docker-based `mcp__markitdown__convert_to_markdown` MCP tool to the native `markitdown` CLI (0.1.6, on PATH); dropped the host→container `file://` mount caveat; container decommission is by image ancestor (`--filter ancestor=markitdown-mcp:latest`), not by the non-existent name `markitdown-mcp`
- [session-inbox-monitor-received-msg-fp.md](concepts/session-inbox-monitor-received-msg-fp.md) — sibling of [[delegate-task-negative-trigger-fp]]: `session-inbox-monitor` FP-fires on RU «обработай полученное письмо» (N1) because its literal+routed carve-out points at `inter-session-peer-discipline`, which **isn't installed** → no competitor, nearest inbox-skill wins. Borderline (neg 2/3, EN twin clean), body-load self-corrects. **Open** (follow-up task). New principle: *a routed negative competes only if its route target is installed*
- [task-format-design.md](concepts/task-format-design.md) — new `task-format` skill v0.1.0: public reference for the on-disk `.tasks/STATUS.md` block format the poller parses (header regex, status emoji, `**Weight:**` / `**Notify:**` / `**Requirements:**`); ships with `factory` where the internal wiki/MCP-source can't reach; distinct from [[delegate-task]] (MCP-tool delegation) and [[using-tasks]] (board mechanics); RED 3-baseline / GREEN 2-verify per writing-skills; ground truth = `status-md.ts` + `claim.ts` + `fleet-router.js`
## Packages
<!-- (none yet) -->
## Sources
<!-- (none yet) -->
- [pi-extension-headless-ritual.md](concepts/pi-extension-headless-ritual.md) — agent_end (not agent_settled) for followUp injection; mode guard (`print` not hasUI); loop-guard flag-before-send; opt-in mirrors skill
**Не читать. Не править.** Канон — mappa (`mcp__mappa__*`): wiki-сущности проекта, конвенции — AGENTS-сущность. Скил: `mappa-knowledge`.

View File

@@ -1,82 +1,3 @@
# Wiki Log # ⛔ Файловый канал закрыт
Append-only operation log. One entry per operation. Format: **Не читать. Не править.** Канон — mappa (`mcp__mappa__*`): wiki-сущности проекта, конвенции — AGENTS-сущность. Скил: `mappa-knowledge`.
```
## [YYYY-MM-DD] <op> | <one-line description>
```
Operations: `init`, `ingest`, `query`, `lint`, `refactor`, `decision`.
Parseable: `grep "^## \[" .wiki/log.md | tail -20`.
---
## [2026-04-28] init | bootstrap empty wiki via project-bootstrap (old layout)
## [2026-04-28] decision | repo-layout — flat `skills/`, committed `dist/`, bash + PS scripts
## [2026-04-28] decision | build-notes — PS 5.1 Compress-Archive backslash bug; build.ps1 via .NET ZipArchive
## [2026-04-28] decision | active-platform — skill chosen over global CLAUDE.md / project memory; default Windows; wired into project-bootstrap
## [2026-04-28] refactor | wiki-realignment — fixed project-bootstrap Step 3 to create Karpathy-canonical layout
## [2026-04-28] refactor | this repo's `.wiki/` migrated to canonical layout (SUMMARY.md→index.md, source/→concepts/, added log.md/overview.md/CLAUDE.md schema, raw/README.md)
## [2026-04-28] decision | context7-setup — switched to official plugin; --api-key injected into plugin's .mcp.json; three manual MCP entries removed
## [2026-04-28] decision | setup-context7 skill — formalized the install/migrate algorithm; using-context7 gets a Prerequisites pointer; build.sh PS multi-arg bug fixed (loop instead of comma-joined -Names)
## [2026-04-28] verify | setup-context7 — Vitya ran using-context7 in a session that needed setup; Prerequisites pointer triggered setup-context7; full flow worked end-to-end. Pattern (policy + setup split) validated.
## [2026-04-28] decision | skill-vs-plugin — documented when a bare skill suffices vs when a plugin is required (slash commands, hooks, sub-agents, MCP via marketplace)
## [2026-04-28] decision | skill-versioning — added `version: 1.0.0` to 6 infra skills' frontmatter; project-bootstrap now writes .wiki/concepts/bootstrap-manifest.md per project
## [2026-04-28] refactor | wiki split — `wiki-maintainer` renamed to `using-wiki` (policy); new `setup-wiki` skill owns greenfield creation and canon migration; `project-bootstrap` Step 3 delegates
## [2026-04-28] refactor | tasks split — `task-status-wiki` renamed to `using-tasks` (policy); new `setup-tasks` skill owns greenfield + interactive migration (no auto-parsing of old flat STATUS.md); `project-bootstrap` Step 4 delegates
## [2026-04-28] refactor | this repo's `.tasks/` migrated to canonical layout — flat `## Done`/`## Backlog` replaced by emoji-status board (7 ⚪ Ready blocks); historical Done entries dropped (preserved in git log); `.bak` ignored via .gitignore
## [2026-04-28] cleanup | removed stale `~/.claude/skills/{wiki-maintainer,task-status-wiki}/` installs (replaced by `using-wiki`/`using-tasks`); 16 skills installed, no duplicates; context7 plugin (mcp__plugin_context7_context7__*) confirmed live after restart
## [2026-04-28] decision | install-portability — `install.sh`/`build.sh` patched to drop `mapfile`+`find -printf`; stock macOS (bash 3.2 + BSD find) now works; verified on git-bash (16 skills discovered, sorted, installed; build.sh produces archive)
## [2026-04-29] decision | projects-meta-skills — built `setup-projects-meta` (8-phase install of projects-meta-mcp + auth.toml + MCP registration) and `using-projects-meta` (runtime policy with local-first rule and two-step mutation); skill pair pattern applied for the 4th time (context7 / wiki / tasks / projects-meta); both built + installed; visible to the harness
## [2026-04-30] refactor | projects-meta-skills — wiki path canon corrected: `~/projects/.wiki` → `~/projects/projects-wiki/` (clone root), content at `~/projects/projects-wiki/.wiki/`. Old path caused write/read mismatch bug (fixed upstream in commit `621a69f` of `projects-meta-mcp`). Setup-projects-meta Phase 1 now detects legacy clone, Phase 4 re-clones to canon. Lesson: pull shared resources before relying on cached anchors
## [2026-04-30] decision | using-projects-meta v1.1.0 — added mandatory Step 0 freshness gate: probe `meta_status`; if cache_age > 10min or errors > 0, `node dist/sync.js`; for shared-wiki writes unconditional `git -C ~/projects/projects-wiki pull --ff-only`; 401/403 → loud failure to user. Codifies the same-session lesson — `projects-meta` is a multi-machine bus, stale cache breaks read accuracy and write atomicity
## [2026-04-28] decision | project-bootstrap@1.1.0 — added Step 5.6: detects `superpowers@claude-plugins-official` via `~/.claude/plugins/installed_plugins.json` and prints install command + upstream link if missing; chat-only, never auto-installs (slash commands aren't callable from a skill, and silent plugin install is overreach)
## [2026-04-28] doc | README.md + README.ru.md — new "Using skills in projects" / "Использование в проектах" section after install quick-start; describes project-bootstrap workflow (git, .gitignore, README, .wiki/, .tasks/, CLAUDE.md, manifest, superpowers-plugin check) and the init/upgrade modes
## [2026-04-30] refactor | project-bootstrap re-run on this repo (upgrade mode) — setup-wiki noop, setup-tasks noop, CLAUDE.md unchanged (matches template), bootstrap-manifest.md written: project-bootstrap@1.1.0 / setup-wiki@1.0.0 / setup-tasks@1.0.0
## [2026-04-30] decision | project-bootstrap@1.2.0 — CLAUDE.md template gains `check across all projects` (verbatim trigger from using-projects-meta description); installs auto-load cross-project tasks + shared-wiki access in every bootstrapped repo; no Step 5.7 dependency-check mirror — Prerequisites pointer in using-projects-meta is self-correcting; local CLAUDE.md, both READMEs, dist/.skill, projects-meta-skills concept page synced
## [2026-04-30] decision | Step 5.7 mirror of Step 5.6 (projects-meta-mcp dependency detector / `setup-projects-meta` recommendation) accepted as future work; tracked as ⚪ Ready task `[bootstrap-recommend-projects-meta]`; deferred until first observed fresh-machine miss so detector signal is informed by real failure mode; concept page `projects-meta-skills.md` updated to reflect new stance
## [2026-04-30] decision | project-bootstrap@1.3.0 — Step 5 upgrade path turned idempotent: read existing CLAUDE.md → substring-diff vs template → confirm → append-only-missing; closes silent gap where pre-1.2.0 projects never picked up new canonical triggers (`check across all projects`, `we're on Windows`); platform line preserved if user pinned a non-host one; concept page `bootstrap-claude-md-merge.md` written; README CLAUDE.md row updated to note idempotent merge
## [2026-05-01] decision | pulling-before-work — new policy skill (v1.0.0): one `git pull --ff-only` at session start + on-demand re-sync; bootstrap template gains canonical trigger; project-bootstrap 1.3.0→1.4.0
## [2026-05-01] decision | project-discipline — new policy skill (v0.1.0): four cross-project rules (conventions-over-defaults, master-only, semver-bumping, ask-before-push); bootstrap template gains canonical trigger; project-bootstrap 1.4.0→1.5.0; skill-versioning concept extended to all skills
## [2026-05-01] ingest | shared-wiki packages/claude-skills — каталог всех 20 скиллов опубликован в projects-wiki (3 commits: page + index + log on Gitea, ae2cc9a..001cdd0); группировка bootstrap / wiki+tasks / MCP / caveman / discovery+platform; cross-link с concepts/setup-using-skill-pair и packages/projects-meta-mcp
## [2026-05-05] ingest | concepts/interns-design
## [2026-05-05] decision | interns-skills-mvp — shipped `setup-interns` v0.1.0 (8-phase install: detect `.common/lib/interns-mcp/`, `pip install -e`, `.common/secrets/interns.env` write, `mcpServers.interns` registration with absolute Python interpreter + `cwd`) and `using-interns` v0.1.0 (runtime policy mirroring project-discipline Rule 4: ask-mode default, conversational grant/revoke, always-ask paths for `.env`/secrets/keys/SSH/credentials with transitive rule, cost-cap >$0.10, session-end reset; routing hints for `bulk_text_read` + `transcript_distill`); `project-bootstrap` 1.5.0→1.6.0 with canonical CLAUDE.md trigger `delegate to interns when allowed` between `follow project discipline` and `we're on Windows`, Step 5 commentary paragraph, manifest table extended with both new skills + `project-discipline` row; root `CLAUDE.md` dogfood updated; both READMEs written; descriptions verified (setup-interns 899 chars, using-interns 814 chars, both under 900 budget); all three rebuilt + installed + listed by harness with full descriptions (no H1 fallback)
## [2026-05-05] ingest | concepts/bootstrap-skill-deps-check
## [2026-05-05] decision | bootstrap-skill-deps-check — `project-bootstrap` 1.6.0→1.7.0 collapses Step 5.6 from a single-skill detector (only `superpowers` plugin) into a generic `trigger → fulfiller` table walker. Map embedded in SKILL.md (9 rows: caveman, superpowers plugin, using-wiki, using-tasks, using-projects-meta, pulling-before-work, project-discipline, using-interns, active-platform); `kind: skill` vs `kind: plugin` flag drives the install command emitted in the recommendation block. Algorithm: read project's CLAUDE.md → match each line vs map (substring + tolower, mirrors Step 5 idempotent merge) → for each canonical match check disk (`~/.claude/skills/<name>/SKILL.md` or `installed_plugins.json` key); print one chat-only block listing every missing fulfiller + install commands, or one ✅ line if all satisfied. User-custom lines silently skipped; removed canonical lines silently skipped (respects user opt-out). Hard rule "never auto-install" carries over verbatim. Subsumes the deferred `[bootstrap-recommend-projects-meta]` task (closed by absorption — generic step handles `using-projects-meta` along with everything else). MCP-server-backed skills only check the `using-X` policy skill; `setup-X` self-fires on first use via Prerequisites pointer, bootstrap doesn't duplicate.
## [2026-05-05] decision | compress-dedup — `skills/compress/` was a stripped-down byte-for-byte dupe of `skills/caveman-compress/` (scripts/ identical SHA256 across all 7 files; SKILL.md diff = `name:` + Process step 2; descriptions textually identical = arbitrary harness tie-break + double-counted listing budget). Kept `caveman-compress` canonical: it carries README.md (benchmarks table + caveman-toolkit branding) and SECURITY.md (Snyk false-positive writeup), and matches the caveman-* prefix invariant. Ported the better Process-step wording from `compress` into `caveman-compress` (`cd <directory_containing_this_SKILL.md>` instead of brittle `cd caveman-compress` which assumes cwd). Added `version: 1.0.0` to caveman-compress frontmatter (first versioned release; aligns with skill-versioning concept). Deleted: `skills/compress/`, `dist/compress.skill`, `~/.claude/skills/compress/` (manual prune — install.sh has no prune step; future `[install-ps1]` task should add `--prune` flag). Rebuilt + reinstalled `caveman-compress`. Slash-command impact: `/compress` removed; `/caveman-compress` + `/caveman:compress` (toolkit-canonical) remain. Concept page `concepts/compress-dedup.md` written (rationale + rejected alternatives: alias-stub has no harness mechanism; "keep both" wastes listing budget; "delete caveman-compress" loses README + SECURITY).
## [2026-05-05] design | active-platform-eval (paused) — combined `[active-platform-tuning]` + `[active-platform-eval]` into one workstream (eval *is* the tuning mechanism; "wait for 5 real signals" was a placeholder). Spec written at `.wiki/concepts/active-platform-eval-design.md`: 20-query trigger eval set balanced ≥3 should-trigger per OS (Win/Lin/Mac) + near-miss negatives, run in `skill-creator/scripts/run_loop.py` (5 iter, train/test split, model `claude-opus-4-7`) **in parallel** with manual body sweep (WSL clarity, BSD/macOS expansion, ambiguity policy). Workspace at `.tasks/active-platform-eval/` (eval-set.json committed, iterations gitignored). Version bump 1.0.0 → 1.1.0 planned (MINOR). Pre-flight verified: `claude` CLI at `C:\nvm4w\nodejs\claude.ps1` (Claude Code 2.1.128) + `run_loop.py` present in skill-creator install — both autoloop deps satisfied, no fallback needed. Per-task file at `.tasks/active-platform-eval.md`. Paused at user request before eval-set authorship; resume point is Q2 (write 20 queries solo vs run skill-creator HTML-review template for user edits first). Also fixed in same pause: `[install-ps1]` STATUS scope expanded to "paired install.sh + install.ps1, cross-platform parity, --prune flag" (lesson from `[compress-dedup]`).
## [2026-05-05] ingest | concepts/interns-repo-read-design
## [2026-05-06] ingest | concepts/hermes-skills-rollout-design
## [2026-05-07] ingest | concepts/tdd-criteria-design
## [2026-05-07] review | tdd-criteria v0.2.0 — 4 findings applied: trigger-loophole fix (removed session-authorship clause), composite-tasks + refactoring sections, expanded file-extension list, clarified wrapper line-count + spike-survivor fallback + foreign-schema fix; design doc synced
## [2026-05-10] decision | project-bootstrap-meta-isolation — v1.11.0 ships meta-isolation block in `.gitignore` template + Step 1 upgrade-case append; restores agent meta-paths visibility against global `core.excludesFile`; smoke-tested greenfield + negative control + idempotency
## [2026-05-22] ingest | concepts/interns-grep-audit-design
## [2026-05-25] decision | session-handoff-skill-design — design rationale for the `session-handoff` skill captured in wiki after cluster 7/7 closure; sliding overwrite of `.tasks/NEXT_SESSION.md`, phrase whitelist + substantive-commit heuristic, opt-in PostToolUse hook, orient+ask default, source: `~/projects/.workshop/.archive/2026-05-24-session-handoff-skill.md` Round 1 + Round 2
## [2026-05-25] decision | install-cross-platform — `install.{ps1,sh}` paired-script parity contract documented; `--prune` / `-Prune` flag rationale (combined-with-install, global-scan ignores names filter, default-off, print-and-delete no prompt); shipped in commit `6cf0e98` with `[skip-tdd: wrapper]` carve-out + smoke-test evidence; closes 2/3 of `[install-ps1]` acceptance (the doc + flag), `dist/`-prune analogue deferred to `build` scripts
## [2026-05-25] decision | install-cross-platform extended to build scripts — `build.{ps1,sh}` get the symmetric `--prune` / `-Prune` flag (removes `dist/<name>.skill` where `<name>` is not in `skills/`). Bash delegation to `powershell.exe -File build.ps1` does NOT forward the flag — bash runs prune itself against the shared `dist/`. Both paths smoke-tested with fake stale .skill files against real dist/. Closes `[install-ps1-build-prune-followup]`.
## [2026-06-09] decision | delegate-task-negative-trigger-fp — `delegate-task` 0.2.0→0.2.1 (PATCH): fixed 5/5-consistent false-positive on «создать задачу себе». Root cause: self-task phrase shares stem «создать задачу» with the «создать задачу на агента» positive trigger; the abstract "Does NOT apply when doing the work yourself" carve-out can't beat a literal stem-match under the 1%-rule. Fix: made the negative literal + routed («создать задачу себе» / «task for myself» / «поставить себе задачу» → using-tasks) in description + body disambiguator («на агента»/«агенту» = delegate; «себе» = own board). Re-verified via fresh-context subagent trigger run: positives 5/5 (no regression), negative 4/5 → using-tasks (was 0/5); the 1 residual miss was an eval-harness artifact (forced skill-name-before-reasoning), not description ambiguity. Concept page written; reusable principle = put the exact colliding negative phrase with an explicit →sibling route, literal beats abstract.
## [2026-06-09] decision | delegate-task-session-break — `delegate-task` 0.2.1→0.2.2 (PATCH): authoring side of the `session_break` marker (consumer = using-tasks v1.2.0). Added pre-flight Q6 (after notify): "Session-break после этой задачи? (domain-switch / milestone / heavy infra)"; if yes → set optional template field `session_break: true | "<hint>"` (trailer, next to weight/notify/allow_upgrade; same lowercase frontmatter key using-tasks reads). Usage guidance lists three set-it cases; What-NOT-to-do bullet warns against setting it routinely (it's a real-boundary marker, not a default). Wiki concept page concepts/delegate-task-session-break.md + index. Pairs with using-tasks-session-break.
## [2026-06-09] decision | using-system-snapshot — new skill v0.1.0: thin read-only wrapper over the single `mcp__projects-meta__meta_system_snapshot` call (poller status + local docker containers + cached cross-project task summary). Replaces the scatter of `tasklist` + `docker ps` + manual `meta_status`. Core rule: no claim about poller / local-docker / task-load state without calling the tool in the current turn (memory + stale earlier snapshot ≠ evidence). Output = three lines, one per section (docker lists only problem containers; tasks gives Σ active/blocked + busiest 2–3). Liveness split documented: poller+docker live, tasks from cache (defer precise work to using-projects-meta Step 0). Scope boundaries: deep single-container diagnosis → using-vds-ops / `docker logs`; docker section is LOCAL, not the VDS. Read-only, no per-session grant (mirrors using-vds-ops). Output shape verified by a live call 2026-06-09. Concept page concepts/using-system-snapshot-design.md + index. TDD N/A (markdown policy artifact); behavioral smoke-test = paired skill-using-system-snapshot-review task.
## [2026-06-09] review | using-system-snapshot v0.1.0 — VERDICT PASS on all 3 acceptance criteria (skill-using-system-snapshot-review). Tool contract verified by a live `meta_system_snapshot` call (output matches the documented `poller`/`docker`/`tasks` shape exactly). Behavioral trigger smoke = 9 fresh-context subagents over a simulated registry (real descriptions + using-vds-ops/using-projects-meta/using-tasks competitors, no expected-answer hint): 4/4 positives → using-system-snapshot; VDS-logs → using-vds-ops; mutate/full-board → using-projects-meta; `docker-compose.yml` edit → none (no FP on "docker" keyword). No-claim-without-snapshot rule explicit in 4 places; three-line output format confirmed achievable against the live payload. 3 informational findings (none blocking): (1) cross-project task-COUNT phrasings overlap with using-projects-meta — by-design, snapshot defers precise per-task work; (2) LOCAL-container deep diagnosis is unowned — vds-ops incident triggers grab local containers its VDS-only tools can't reach (vds-ops scoping, not this skill); (3) deployment scaffold missing — skill committed but not installed to `~/.claude/skills/`, not in `hermes/mapping.yaml`, no -install/-hermes-mapping/-test-trigger baseline tasks; recommended follow-ups (hermes mode could be `auto`, read-only skill). Review outcome appended to concepts/using-system-snapshot-design.md.
## [2026-06-09] decision | using-tasks-status-archival — `using-tasks` 1.2.0→1.3.0 (MINOR): added done-task archival rule to fix STATUS.md bloat ("huge STATUS.md" complaint). When ≥10 🟢 done blocks pile up — checked at session start (step 7) and after close (Task completion step 7) — move them verbatim to `.tasks/archive/YYYY-MM.md` (append, one file per month, one-time header), leaving only 🔴/🟡/⚪/🔵 on the board; committed on its own. Did NOT follow the task's literal instruction to replace `Read STATUS.md` with `tasks_get_status` for orientation: that tool returns a single task's live status by known slug (`{status, found}`) and cannot enumerate the board, and `tasks_aggregate` is cross-project + cache-based + doesn't index ready/done (its docs say read STATUS.md directly for the current project). So orientation stays a local board-read (kept cheap by archival); skill now warns against both tools for board enumeration and points `tasks_get_status` at its real single-task use. Core goal (kill the bloat) met by archival alone. Concept page concepts/using-tasks-status-archival.md + index. TDD N/A (markdown policy). Deviation flagged for paired review task using-tasks-status-read-perf-review.
## [2026-06-09] decision | using-tasks-session-break — `using-tasks` 1.1.0→1.2.0 (MINOR): added the `session_break` marker. Task author sets `session_break: true | "<hint>"` in task frontmatter (mirrored as `**Session break:**` on the local board); after the task closes 🟢, before `tasks_claim_next`, an autonomous agent prints the verbatim line `🔚 SESSION BOUNDARY — [slug] закрыта. Рекомендую завершить текущую сессию. Следующий трек: [value | "см. STATUS.md"]` and stops instead of chaining the next task. Absent → behaviour unchanged. Enforced in Task completion step 6 + Rules bullet + format docs. Marker not heuristic: the stop-point is an authoring choice, not a runner guess.
## [2026-06-09] review | using-tasks-status-archival v1.3.0 — VERDICT PASS 3/3 (using-tasks-status-read-perf-review). Criterion «ориентация через `tasks_get_status`, не Read» is satisfied by a **validated deviation**, not a literal swap: re-verified against the live tool schema that `tasks_get_status(target_project, slug)→{status, found}` takes a required slug and returns ONE task — it cannot enumerate the board, so it cannot drive orientation; the implementer correctly rejected the impossible instruction and fixed the real problem (bloat→archival). No regression: orientation still reads local STATUS.md (Session start §2) and the «what's next» flow still reads the board — change is purely additive. Archival rule clear & complete (≥10 threshold, two trigger points, monthly append-only archive, verbatim blocks, dedicated commit, cross-referenced). One informational non-blocking note: this repo's own STATUS.md (>10 🟢) would itself trip the rule — dogfooding tracked separately as tasks-board-cleanup-2026-05. No follow-up tasks. Verdict appended to concepts/using-tasks-status-archival.md.
## [2026-06-09] decision | delegate-task-review-weight — `delegate-task` 0.2.2→0.2.3 (PATCH): Step 5 (paired `<slug>-review` task) now sets an explicit `weight`, inherited from the impl-task with a `needs-claude` floor (impl `needs-human`→review `needs-human`; `needs-claude`→`needs-claude`; `cheap-ok`→`needs-claude`). Root cause of commit `c0af151` ("add Weight: needs-claude to 4 review tasks — reconciler was skipping them"): the authoring skill omitted `weight` on review tasks, making them invisible to fleet routing. Floor (not pure inheritance) chosen to stay internally consistent with the skill's own "What NOT to do" bullet that forbids `cheap-ok` for review tasks — a `cheap-ok` impl would otherwise propagate a forbidden `cheap-ok` review. Added a What-NOT-to-do bullet against weightless review tasks. Concept page concepts/delegate-task-review-weight.md + index. TDD N/A (markdown policy artifact).
## [2026-06-11] decision | task-format — new skill v0.1.0: public reference for the `.tasks/STATUS.md` task-block format the autonomous poller parses. Motivation: the field rules (`**Weight:**` capability/cost tier, `**Notify:** <owner>/<repo>` inbox target, header regex, status emoji) lived only in internal sources (`projects-meta-mcp/src/lib/status-md.ts` parser + `status-md-writer.ts` + `.common/.wiki/concepts/agents-task-runner-ops.md`); skills ship with `factory` to external users, the wiki/MCP-source don't. Scope kept distinct from delegate-task (creates tasks for others via `tasks_create`, the tool emits the format) and using-tasks (board claim/close mechanics) — task-format is the byte-level field reference for hand-edited blocks. Ground truth verified against source: header `/^##\s+(\S+)\s+\[([^\]]+)\]\s+—\s+(.+)$/u`; Weight ∈ {cheap-ok, needs-claude, needs-human}; claim gate excludes only `needs-human` (`claim.ts`), but a *missing* Weight finds no backend tier (`fleet-router.js` resolveBackend) → poller parks to 🔵 blocked, so Weight is operatively required for pickup. TDD per writing-skills: RED = 3 baseline subagents w/o skill (2/3 used `###`/bullet headers the parser can't recognize, 2/3 omitted Weight inventing `risk`/`tier`/`claimable-by`, 2/3 put notify in prose, 1/3 used 🟢 for ready); GREEN = 2 fresh subagents w/ skill, both parser-valid incl. correct `needs-human` for the critical-infra scenario; REFACTOR = no new loopholes. Reference skill ~900 words (loads only when authoring a task block). Concept page concepts/task-format-design.md + index. Not yet installed to `~/.claude/skills/` or added to hermes mapping — deferred follow-up (mirrors using-system-snapshot deployment-scaffold note).
## [2026-06-09] decision | using-markitdown-cli-migration — `using-markitdown` 1.0.0→1.0.1 (PATCH): rewrote the skill from the Docker-based `mcp__markitdown__convert_to_markdown` MCP tool to the native `markitdown` CLI (v0.1.6, on PATH). Tool block now `markitdown <path|url>` → stdout (or `-o file`); removed the whole "Docker-mount caveat (READ FIRST)" section (host→container `file://` translation + `[Errno 2] /c:/Users/...` symptom are gone — CLI sees the full host FS). Updated the ingest pattern (use `-o` straight into `.wiki/raw/`), the gotchas table (`command not found` → check `markitdown --version`, install `pip install markitdown[all]`; dropped the MCP "tool not available / ToolSearch" row), and the contrast-table header (CLI, not MCP). Description frontmatter (the WHEN-to-use triggers) left unchanged. Container decommission: the task's literal `docker stop/rm markitdown-mcp` had no target — no container is named that; the MCP spawns anonymously-named containers from `markitdown-mcp:latest` per session (3 had piled up). Removed all by image ancestor (`docker rm -f $(docker ps -aq --filter "ancestor=markitdown-mcp:latest")`), verified none remain. Left the `mcpServers.markitdown` entry in `~/.claude.json` untouched (out of scope; a container will respawn next session until it's deregistered — flagged as a follow-up). Concept page concepts/using-markitdown-cli-migration.md + index. TDD N/A (markdown skill).
## [2026-06-17] decision | session-inbox-monitor-received-msg-fp — finding from `session-inbox-monitor-test-trigger` (VERDICT PASS, clean session, 7 unprimed clean-context subagents: pos 4/4 incl. CLAUDE.md-line P4, neg 2/3). The 1 FP: RU «обработай полученное письмо из инбокса» (N1) routed to `session-inbox-monitor`; the EN twin (N3) and the multi-machine-backend negative (N2) routed to `none` cleanly. Root cause = a new dimension on top of [[delegate-task-negative-trigger-fp]]: the carve-out is already literal+routed (`NOT for handling a received message → inter-session-peer-discipline`), but the route target `inter-session-peer-discipline` is **not installed** → no real competitor, so the nearest in-domain skill (session-inbox-monitor) wins by default; non-deterministic, self-corrects on body-load (cost = one wasted skill-load, not a wrong action; isomorphic to [[using-tasks-session-break]] session_break). New page concepts/session-inbox-monitor-received-msg-fp.md + bidirectional link from concepts/delegate-task-negative-trigger-fp.md + index. New reusable principle: a routed negative competes only if its route target is installed. Status OPEN — follow-up task session-inbox-monitor-received-msg-fp (options a: harden description / b: install sibling / c: accept informational). Not a memory entry by owner direction — knowledge belongs in the project wiki.
## [2026-06-17] decision | session-inbox-monitor-received-msg-fp RESOLVED via option (b) — installed `inter-session-peer-discipline` (existed in sources since 2026-06-16, was not installed → exact root cause confirmed). install.ps1 -Names, byte-identical parity. FP-twin verified clean: fresh clean-context subagent on the N1 phrase now routes to inter-session-peer-discipline (IN_REGISTRY: yes), not session-inbox-monitor — carve-out now has a real competitor. session-inbox-monitor description untouched (option (a) rejected as whack-a-mole; (c) as latent hole). Governance: peer workshop proposed (b) as a "ruling"; per the freshly-installed [[inter-session-peer-discipline]] (peer = proposal not authority, scope needs human ratification) it was surfaced as a recommendation and ratified by the user — live dogfood of the skill's own purpose. concepts/session-inbox-monitor-received-msg-fp.md Status section updated open→resolved. Tail: inter-session-peer-discipline now installed but not in hermes/mapping.yaml — possible red build, flagged as separate follow-up.
## [2026-08-12] ingest | pi-extension-headless-ritual — agent_end/mode-guard/loop-guard lessons from session-close-ritual build
## [2026-08-13] refactor | context7-setup — concept updated to CLI-first canonical (setup-context7 v2.0.0 migration, 2026-08-12): ctx7 CLI + key in ~/.config/projects-secrets/ctx7.env, plugin + manual MCP removed; plugin era demoted to rollback reference; whoami!=key-check gotcha recorded; index entry refreshed

View File

@@ -1,29 +1,3 @@
--- # ⛔ Файловый канал закрыт
title: claude-skills overview
type: overview
updated: 2026-04-28
---
# claude-skills — overview **Не читать. Не править.** Канон — mappa (`mcp__mappa__*`): wiki-сущности проекта, конвенции — AGENTS-сущность. Скил: `mappa-knowledge`.
Joint workshop where Vitya and Claude develop, test, and store Claude skills. Both editable sources (`skills/<name>/`) and built archives (`dist/<name>.skill`) live here, so a fresh machine can clone the repo and install every personal skill in one command.
## Components
- **`skills/`** — editable skill sources, one folder per skill (each with `SKILL.md` + optional `assets/`).
- **`dist/`** — built `.skill` archives, committed so installs don't need a build toolchain on the target.
- **`scripts/`** — `build.sh` / `build.ps1` (zip sources → archive), `install.sh` (copy sources → `~/.claude/skills/`).
- **`.wiki/`** — Karpathy LLM Wiki for design decisions and gotchas. See [CLAUDE.md](CLAUDE.md) for schema.
- **`.tasks/`** — task board (`STATUS.md`).
- **`CLAUDE.md`** — repo-level agent instructions (skill triggers).
## Where to look
- New here? → [concepts/repo-layout.md](concepts/repo-layout.md), then `README.md`.
- Working on a skill? → edit `skills/<name>/`, then `bash scripts/install.sh <name>` (or `pwsh scripts/build.ps1 <name>` to refresh the archive).
- Tracking work? → [.tasks/STATUS.md](../.tasks/STATUS.md).
- Made a non-trivial decision? → add a `concepts/<topic>.md` page, link from [index.md](index.md), append a line to [log.md](log.md).
## Cross-references
This page intentionally stays short. The substantive material lives in `concepts/` (decisions, gotchas) and the [index](index.md) catalog.

View File

@@ -8,8 +8,27 @@ check across all projects
pull remote before work pull remote before work
session handoff: read on start, write on end session handoff: read on start, write on end
inbox monitor: raise on start inbox monitor: raise on start
session sync: write to mappa
follow project discipline follow project discipline
follow tdd-criteria follow tdd-criteria
delegate to interns when allowed delegate to interns when allowed
recommend, don't menu recommend, don't menu
we're on Windows we're on Windows
mappa sync: run on start
<!-- mappa:canon-block (auto; do not edit) -->
## Mappa canon
**Gates (canon/gates — shared):** краткая суть; полный текст — `wiki_get(slug='canon/gates', full=true)`
- Г1. Знание и артефакты → mappa, не файлы — durable-знание и артефакты проекта живут в mappa; файловые каналы (`.brainstorm/`, `.tasks/`, `.wiki/`) и «сохранить рядом с проектом» закрыты.
- Г2. Контракт каналов — письмо (inbox) — носитель вердиктов/указаний/находок, полным телом; комментарии на тасках — короткий след. Адресация `about`/`to`/`thread` (XOR); lifecycle `ack`/`resolve`/`cancel`.
- Г3. Поиск до угадывания — не угадывать slug/роут: сначала `search`/`wiki_search`; `wiki_get` без project = shared; общая память — `search(mode='recall')`.
- Г4. Адресация и слаги — рефы полными именами (`[[task:N]]`/`[[wiki:slug]]`); слаги kebab-case, латиница; номера `task:N` выдаёт сервер.
- Г5. .mappa-гейт — папка участвует в mappa-операциях только с маркером `.mappa`; нет маркера → сказать человеку, мутации — отказ.
- Г6. Секреты — в mappa не пишутся (422); только `secret:<path>`-рефы, значения мимо.
- Г7. Degraded-режим — mappa недоступна: читать кэш `.mappa/` (canon/methodology/runbooks), мутации → `.mappa/pending/`; нет кэша → стоп, не импровизировать.
- Г8. Перед работой с вики/каноном — первым действием прочитать канон-блок AGENTS.md проекта.
- Г9. Живое состояние до заявления — статус заявлять только по свежему чтению mappa, не по памяти/кэшу/ответу create.
**Entity → runbook (runbooks/index — shared):** task → [[runbooks/tasks]] · wiki → [[runbooks/wiki]] · inbox → [[runbooks/inbox]] · **thread** → [[runbooks/threads]] · session → [[runbooks/session]] · search → [[runbooks/search]] · issue → [[runbooks/issue]] · **intent** → [[runbooks/intent]] · requirements → [[runbooks/requirements]] · plan → [[runbooks/plan]] · comment → [[runbooks/comment]] · tag → [[runbooks/tag]] · attachment → [[runbooks/attachment]] · release → [[runbooks/release]] · brainstorm → [[runbooks/brainstorm]] · agent → [[runbooks/agent-operator]] · repo → [[runbooks/repo-commit]] · project → [[runbooks/project]] · skill → [[runbooks/skill]] · entity-слой → [[runbooks/entity]] · sched → [[runbooks/sched-telemetry]]
**Methodology:** `methodology/kzntsv`
**Canon version:** 4
<!-- /mappa:canon-block -->

View File

@@ -25,8 +25,8 @@ A shared workspace where Claude and I author, debug, and ship skills together:
git clone <repo> skills git clone <repo> skills
cd skills cd skills
bash scripts/install.sh # copies every skills/* into ~/.claude/skills/ bash scripts/install.sh # copies every skills/* into ~/.claude/skills/
# or only specific ones: # or only specific ones (mappa-* skills install from the `mappa` repo — see mappa-bootstrap):
bash scripts/install.sh using-wiki caveman bash scripts/install.sh caveman tdd-criteria
``` ```
**Linux / macOS (bash):** **Linux / macOS (bash):**
@@ -35,8 +35,8 @@ bash scripts/install.sh using-wiki caveman
git clone <repo> skills git clone <repo> skills
cd skills cd skills
bash scripts/install.sh # copies every skills/* into ~/.claude/skills/ bash scripts/install.sh # copies every skills/* into ~/.claude/skills/
# or only specific ones: # or only specific ones (mappa-* skills install from the `mappa` repo — see mappa-bootstrap):
bash scripts/install.sh using-wiki caveman bash scripts/install.sh caveman tdd-criteria
``` ```
The install target can be overridden with `CLAUDE_SKILLS_DIR=/path bash scripts/install.sh`. The install target can be overridden with `CLAUDE_SKILLS_DIR=/path bash scripts/install.sh`.
@@ -52,10 +52,9 @@ project's folder and it will, in one pass:
- initialize `git` (if missing) and write a sane `.gitignore` - initialize `git` (if missing) and write a sane `.gitignore`
- create a starter `README.md` - create a starter `README.md`
- lay out `.wiki/` per the [Karpathy LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) (delegated to [`setup-wiki`](skills/setup-wiki/)) - register the project meta in **mappa** (wiki/task-сущности проекта; file-based `.wiki/`/`.tasks/` closed 2026-08-25)
- lay out `.tasks/` with the canonical task board (delegated to [`setup-tasks`](skills/setup-tasks/))
- write `AGENTS.md` (canon) with skill triggers (`use project wiki`, `use task management system`, `check across all projects`, `we're on Windows`) plus a `CLAUDE.md` legacy pointer - write `AGENTS.md` (canon) with skill triggers (`use project wiki`, `use task management system`, `check across all projects`, `we're on Windows`) plus a `CLAUDE.md` legacy pointer
- record the skill versions used in `.wiki/concepts/bootstrap-manifest.md` so cross-project layout drift stays debuggable - record the skill versions used in a mappa wiki entity (`concepts/bootstrap-manifest`) so cross-project layout drift stays debuggable
Two modes, picked automatically: **init** for an empty folder, **upgrade** Two modes, picked automatically: **init** for an empty folder, **upgrade**
for an existing project (the skill only fills the gaps and never overwrites for an existing project (the skill only fills the gaps and never overwrites
@@ -119,10 +118,14 @@ an explicit `adapted-from` marker in its frontmatter.
| `loop-me` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — workflow-spec design gate | | `loop-me` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — workflow-spec design gate |
| `review-kit-pi-method` | `author: ours` — pi-native spawn for clean-context review subagents | | `review-kit-pi-method` | `author: ours` — pi-native spawn for clean-context review subagents |
| `command-index` | `author: ours` — just/Makefile command-index convention (standard targets, auto-doc; idea 3/18) | | `command-index` | `author: ours` — just/Makefile command-index convention (standard targets, auto-doc; idea 3/18) |
| `code-search` | `author: ours` — rg-first code search (measured 15 min → 0s; routing: rg / git grep / interns repo_read / grep_audit) |
| `code-review` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — two-axis + Fowler baseline; output: caveman-review format | | `code-review` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — two-axis + Fowler baseline; output: caveman-review format |
| `writing-skills` | `adapted-from: obra/superpowers @ 6.2.0` (MIT) — TDD-for-skills core + ideya 8 self-skill-authoring | | `writing-skills` | `adapted-from: obra/superpowers @ 6.2.0` (MIT) — TDD-for-skills core + ideya 8 self-skill-authoring |
| `web-search` | `author: ours` — search_web tool (pi-extension) + policy: when to search, «без поиска» session-off | | `web-search` | `author: ours` — search_web tool (pi-extension) + policy: when to search, «без поиска» session-off |
| `ops-browser` | `author: ours` — свой **скрытый** браузер агента: отдельный профиль + CDP (`eval`/`fetch` из страницы/скриншоты), `handoff` человеку для пароля/капчи; свой замок `ops.lock` |
| `browser-operator` | `author: ours` — браузер ОПЕРАТОРА (его Chrome/логины): канал по харнессу (Hermes `browser_exec` / pi тул `browser` / CC `chrome-devtools`), аренда «один водитель за раз», границы «человек vs агент», рецепты тяжёлых страниц. Закрывает провал базового прогона 2026-09-11 («куки из Chrome + curl + ввод пароля» мимо канала); анонимные прогоны — `browser-cdp` |
| `review-subagent` | `author: ours` — review_subagent tool (pi-extension): clean-context review by your own model, optional `model` override | | `review-subagent` | `author: ours` — review_subagent tool (pi-extension): clean-context review by your own model, optional `model` override |
| `report-mappa-issue` | `author: ours` — TEMPORARY stopgap: mappa deviation reporting (mail to `mappa` + `.workshop`) while the service is unstable; retire when stabilized |
| all other `skills/*` | `author: ours` | | all other `skills/*` | `author: ours` |
Adaptation policy: a clone is rewritten to our conventions (`.tasks/` boards, Adaptation policy: a clone is rewritten to our conventions (`.tasks/` boards,
@@ -140,7 +143,7 @@ skills/
│ ├── mapping.yaml ← per-skill Hermes-rollout config │ ├── mapping.yaml ← per-skill Hermes-rollout config
│ └── skills/ ← `mode: manual` overrides (Hermes-flavour rewrites) │ └── skills/ ← `mode: manual` overrides (Hermes-flavour rewrites)
├── dist-hermes/ ← pre-converted Hermes-flavour tree (committed) ├── dist-hermes/ ← pre-converted Hermes-flavour tree (committed)
│ ├── <category>/<name>/ ← e.g. software-development/pulling-before-work/ │ ├── <category>/<name>/ ← e.g. software-development/diagnosing-bugs/
│ └── SKIPPED.md ← skip + pending log (auto-generated) │ └── SKIPPED.md ← skip + pending log (auto-generated)
├── scripts/ ├── scripts/
│ ├── build.sh / build.ps1 │ ├── build.sh / build.ps1

View File

@@ -21,8 +21,8 @@
git clone <repo> claude-skills git clone <repo> claude-skills
cd claude-skills cd claude-skills
bash scripts/install.sh # копирует все skills/* в ~/.claude/skills/ bash scripts/install.sh # копирует все skills/* в ~/.claude/skills/
# или конкретные: # или конкретные (mappa-* скилы ставятся из репо `mappa` — см. mappa-bootstrap):
bash scripts/install.sh using-wiki caveman bash scripts/install.sh caveman tdd-criteria
``` ```
Цель установки можно переопределить переменной `CLAUDE_SKILLS_DIR=/path bash scripts/install.sh`. Цель установки можно переопределить переменной `CLAUDE_SKILLS_DIR=/path bash scripts/install.sh`.
@@ -36,10 +36,9 @@ bash scripts/install.sh using-wiki caveman
- инициализирует `git` (если ещё нет) и положит вменяемый `.gitignore` - инициализирует `git` (если ещё нет) и положит вменяемый `.gitignore`
- создаст стартовый `README.md` - создаст стартовый `README.md`
- развернёт `.wiki/` по [паттерну Karpathy LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) (делегируется в [`setup-wiki`](skills/setup-wiki/)) - зарегистрирует мету проекта в **mappa** (wiki/task-сущности; файловые `.wiki/`/`.tasks/` закрыты 2026-08-25)
- развернёт `.tasks/` с канонической доской задач (делегируется в [`setup-tasks`](skills/setup-tasks/))
- запишет `AGENTS.md` (канон) со скилл-триггерами + `CLAUDE.md`-указатель (`use project wiki`, `use task management system`, `check across all projects`, `we're on Windows`) - запишет `AGENTS.md` (канон) со скилл-триггерами + `CLAUDE.md`-указатель (`use project wiki`, `use task management system`, `check across all projects`, `we're on Windows`)
- зафиксирует версии использованных скиллов в `.wiki/concepts/bootstrap-manifest.md`, чтобы дрифт раскладки между проектами оставался отлаживаемым - зафиксирует версии использованных скиллов в mappa wiki-сущности `concepts/bootstrap-manifest`, чтобы дрифт раскладки оставался отлаживаемым
Два режима, выбирается автоматически: **init** для пустой папки и **upgrade** Два режима, выбирается автоматически: **init** для пустой папки и **upgrade**
для существующего проекта (скилл только дозаполняет пробелы и ничего не для существующего проекта (скилл только дозаполняет пробелы и ничего не
@@ -89,8 +88,11 @@ bash scripts/build.sh caveman # один
| `loop-me` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — дизайн-гейт workflow-спец | | `loop-me` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — дизайн-гейт workflow-спец |
| `review-kit-pi-method` | `author: ours` — pi-спавн чистых review-субагентов | | `review-kit-pi-method` | `author: ours` — pi-спавн чистых review-субагентов |
| `command-index` | `author: ours` — конвенция just/Makefile command-index (стандартные таргеты, авто-док; идея 3/18) | | `command-index` | `author: ours` — конвенция just/Makefile command-index (стандартные таргеты, авто-док; идея 3/18) |
| `code-search` | `author: ours` — rg-first код-поиск (замер: 15 мин → 0 сек; роутинг: rg / git grep / interns repo_read / grep_audit) |
| `code-review` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — двухосевость + Fowler-база; формат вывода: caveman-review | | `code-review` | `adapted-from: mattpocock/skills @ 84fdeffd` (MIT) — двухосевость + Fowler-база; формат вывода: caveman-review |
| `writing-skills` | `adapted-from: obra/superpowers @ 6.2.0` (MIT) — TDD-for-skills ядро + идея 8 self-skill-authoring | | `writing-skills` | `adapted-from: obra/superpowers @ 6.2.0` (MIT) — TDD-for-skills ядро + идея 8 self-skill-authoring |
| `ops-browser` | `author: ours` — свой скрытый браузер агента (профиль + CDP + `handoff` человеку, замок `ops.lock`) |
| `browser-operator` | `author: ours` — браузер ОПЕРАТОРА (его Chrome/логины): канал по харнессу (Hermes `browser_exec` / pi тул `browser` / CC `chrome-devtools`), аренда «один водитель за раз», границы «человек vs агент»; анонимные прогоны — `browser-cdp` |
| остальные `skills/*` | `author: ours` | | остальные `skills/*` | `author: ours` |
Политика адаптации: клон переписывается под наши конвенции (доски `.tasks/`, Политика адаптации: клон переписывается под наши конвенции (доски `.tasks/`,

View File

@@ -17,16 +17,11 @@ Do not edit by hand — edit the mapping and re-run the build.
## Pending (deferred to follow-up tasks) ## Pending (deferred to follow-up tasks)
- **delegate-task** — Calls mcp__projects-meta__tasks_create to create tasks in other projects/agents (Gitea commit, cross-project side-effect). Behavioral audit via delegate-task-test-trigger required before promotion to auto. → intended: `mode: auto, category: mcp`
- **meta-host-routing** — Resolves WHERE a project's meta lives before tasks_create / knowledge_ingest / brainstorm-promotion (meta-out-of-repo). Touches projects-meta MCP (tasks_create / knowledge_ingest / meta_status) and routes writes across repos. Review PASS (meta-host-routing-review) but the -install baseline is still open and a tool-side audit (cross-repo MCP writes) is required before auto. Mapping executes task meta-host-routing-hermes-mapping. → intended: `mode: auto, category: meta` - **meta-host-routing** — Resolves WHERE a project's meta lives before tasks_create / knowledge_ingest / brainstorm-promotion (meta-out-of-repo). Touches projects-meta MCP (tasks_create / knowledge_ingest / meta_status) and routes writes across repos. Review PASS (meta-host-routing-review) but the -install baseline is still open and a tool-side audit (cross-repo MCP writes) is required before auto. Mapping executes task meta-host-routing-hermes-mapping. → intended: `mode: auto, category: meta`
- **private-dev-public-publish** — Steps shell out to git / gh / Gitea-API, handle tokens, force-push, and repo deletion/privacy toggles — not a purely stylistic skill. Behavioral audit via private-dev-public-publish-test-trigger required before promotion to auto. → intended: `mode: auto, category: software-development` - **private-dev-public-publish** — Steps shell out to git / gh / Gitea-API, handle tokens, force-push, and repo deletion/privacy toggles — not a purely stylistic skill. Behavioral audit via private-dev-public-publish-test-trigger required before promotion to auto. → intended: `mode: auto, category: software-development`
- **ralph-loop-execution** — Behavioral oracle-loop skill (Verifier / Attempts / Max-Attempts retry loop). NB: source SKILL.md currently lacks YAML frontmatter (no name/description) — cannot auto-convert cleanly until that is fixed. Mapped pending as a placeholder; needs frontmatter + a behavioral audit before any mode decision. - **ralph-loop-execution** — Behavioral oracle-loop skill (Verifier / Attempts / Max-Attempts retry loop). NB: source SKILL.md currently lacks YAML frontmatter (no name/description) — cannot auto-convert cleanly until that is fixed. Mapped pending as a placeholder; needs frontmatter + a behavioral audit before any mode decision.
- **session-handoff** — Writes .tasks/NEXT_SESSION.md (project-scope, sliding overwrite) and reads it on session start. Bidirectional file-system side-effect, opt-in via CLAUDE.md trigger-line. Behavioral audit via session-handoff-test-trigger required before promotion to auto. → intended: `mode: auto, category: productivity`
- **session-inbox-monitor** — Paired SessionStart hook registers itself in ~/.claude/settings.json and sweeps orphaned monitor OS processes (Get-CimInstance | Stop-Process by sentinel+inbox-path); the skill then raises an in-session Monitor on .claude-inbox/. Primary activation is the CLAUDE.md trigger-line `inbox monitor: raise on start` + the injector, not a hermes-trigger. Behavioral gate CLEARED 2026-06-17 — test-trigger + review BOTH VERDICT PASS (activation 3/3 monitor + neg clean; structural hook audit 5 PASS/1 CONCERN, the CONCERN fixed in v0.2.2). STAYS pending on two independent tool-side blockers, NOT on behavioral verification: (1) the SessionStart hook is Windows-PowerShell and needs a Linux port for Hermes factory machines; (2) machine-level side-effects (user-config mutation of ~/.claude/settings.json + Get-CimInstance|Stop-Process kills) need a tool-side audit before auto. Promotion blocked on those two, not on test-trigger/review. → intended: `mode: auto, category: productivity` - **session-inbox-monitor** — Paired SessionStart hook registers itself in ~/.claude/settings.json and sweeps orphaned monitor OS processes (Get-CimInstance | Stop-Process by sentinel+inbox-path); the skill then raises an in-session Monitor on .claude-inbox/. Primary activation is the CLAUDE.md trigger-line `inbox monitor: raise on start` + the injector, not a hermes-trigger. Behavioral gate CLEARED 2026-06-17 — test-trigger + review BOTH VERDICT PASS (activation 3/3 monitor + neg clean; structural hook audit 5 PASS/1 CONCERN, the CONCERN fixed in v0.2.2). STAYS pending on two independent tool-side blockers, NOT on behavioral verification: (1) the SessionStart hook is Windows-PowerShell and needs a Linux port for Hermes factory machines; (2) machine-level side-effects (user-config mutation of ~/.claude/settings.json + Get-CimInstance|Stop-Process kills) need a tool-side audit before auto. Promotion blocked on those two, not on test-trigger/review. → intended: `mode: auto, category: productivity`
- **setup-agents-task-runner** — L2 installer — installs the standing-duty stack (agents-task-runner + watchdog + appeals-inbox) as platform-native OS services (systemd/launchd/winsw), fetches a pinned binary, writes poller-scope.json. Heavy infra side-effects (OS services + binary fetch); mode decision (skip vs manual vs auto) deferred — needs an explicit Hermes-factory applicability audit. Placeholder pending to keep the build green. - **setup-agents-task-runner** — L2 installer — installs the standing-duty stack (agents-task-runner + watchdog + appeals-inbox) as platform-native OS services (systemd/launchd/winsw), fetches a pinned binary, writes poller-scope.json. Heavy infra side-effects (OS services + binary fetch); mode decision (skip vs manual vs auto) deferred — needs an explicit Hermes-factory applicability audit. Placeholder pending to keep the build green.
- **task-format** — Documentational skill — how to write a .tasks/STATUS.md task block the autonomous poller will claim/route/report (block header, status emoji, Weight/Notify/Requirements fields). No tool-side effects; pending a behavioral test-trigger before auto. → intended: `mode: auto, category: productivity` - **task-format** — Documentational skill — how to write a .tasks/STATUS.md task block the autonomous poller will claim/route/report (block header, status emoji, Weight/Notify/Requirements fields). No tool-side effects; pending a behavioral test-trigger before auto. → intended: `mode: auto, category: productivity`
- **task-loop** — Orchestrates the board claim/close/update/heartbeat cycle via mcp__projects-meta__tasks_claim_next / tasks_close / tasks_update / tasks_heartbeat (cross-session claim ownership, irreversible close, Gitea side-effects) and may arm a single long ScheduleWakeup for the explicit long-watch opt-in. Critical-infra-adjacent — touches the same claim/close machinery the unattended poller relies on. Behavioral audit via task-loop-test-trigger required before promotion to auto. → intended: `mode: auto, category: mcp`
- **using-system-snapshot** — Calls mcp__projects-meta__meta_system_snapshot (read-only whole-machine ops snapshot: poller / docker / cross-project task load). Read-only, same class as using-vds-ops / using-wiki-graph; pending a behavioral test-trigger before auto. → intended: `mode: auto, category: mcp`
- **using-vds-ops** — Calls mcp__vds-ops__* tools (read-only, but touches infrastructure). Behavioral audit via using-vds-ops-test-trigger required before promotion to auto. → intended: `mode: auto, category: mcp` - **using-vds-ops** — Calls mcp__vds-ops__* tools (read-only, but touches infrastructure). Behavioral audit via using-vds-ops-test-trigger required before promotion to auto. → intended: `mode: auto, category: mcp`
- **using-wiki-graph** — Calls mcp__wiki-graph__* tools (read-only, parses a .wiki/ corpus server-side). Behavioral audit via using-wiki-graph-test-trigger required before promotion to auto. → intended: `mode: auto, category: mcp`
- **using-yt-tools** — Shells out to yt-dlp + ffmpeg and writes ./yt-cache/ in cwd. Behavioral audit via using-yt-tools-test-trigger required before promotion to auto. → intended: `mode: auto, category: research` - **using-yt-tools** — Shells out to yt-dlp + ffmpeg and writes ./yt-cache/ in cwd. Behavioral audit via using-yt-tools-test-trigger required before promotion to auto. → intended: `mode: auto, category: research`

View File

@@ -1,169 +0,0 @@
# using-tasks
Runtime policy for keeping compressed working context across parallel tasks
in a monorepo. The agent reads and updates `.tasks/` so every session starts
oriented and every switch costs seconds, not minutes.
`using-tasks` governs *usage* of an existing `.tasks/`. Initial creation and
migration to canon are owned by [`setup-tasks`](../setup-tasks/).
> Renamed from `task-status-wiki` at v1.0.0.
## When it triggers
- User is switching between tasks, resuming a paused task, starting a new
one, or asks "where were we" / "what's the status".
- User says: "use task management system", "pause", "switch to X",
"update status".
- Any context-switching or multi-task coordination question in a code
project.
- If `.tasks/` is missing or non-canonical, this skill delegates to
[`setup-tasks`](../setup-tasks/) before doing anything else.
## Structure
```
<monorepo-root>/
└── .tasks/
├── STATUS.md ← board: one block per task, sorted by priority
└── <task-slug>.md ← deep context per task, one file each
```
Commit `.tasks/` to git — decision history is valuable, diffs show how
thinking evolved.
## STATUS.md format
```markdown
# Task Board
_Updated: YYYY-MM-DD_
## 🔴 [task-slug] — short description
**Status:** active | paused | blocked | done
**Where I stopped:** one sentence — the exact thought or action interrupted
**Next action:** one concrete step to resume immediately
**Blocker:** (only if blocked) what is preventing progress
**Branch:** git branch name
---
```
Status legend:
| Emoji | State | Notes |
|---|---|---|
| 🔴 | Active | Currently worked on. **Only one at a time.** |
| 🟡 | Paused | In progress, resumable. |
| ⚪ | Ready | Defined, not started. |
| 🟢 | Done | Kept until merged. |
| 🔵 | Blocked | Waiting on external input. |
## Per-task file format (`<task-slug>.md`)
Sections, in order: **Goal** (one paragraph — what this achieves and why),
**Key files** (`path/to/file.ts:42` style — specific lines when relevant),
**Decisions log** (reverse-chronological, append-only — past entries are
immutable), **Open questions**, **Completed steps**, **Notes** (temporary
hypotheses, links).
## Operations
### Session start
1. Check `.tasks/STATUS.md`. If missing → invoke
[`setup-tasks`](../setup-tasks/) and stop until it returns.
2. Read `STATUS.md`.
3. If user names a task, read its `<task-slug>.md`.
4. Confirm in one sentence: "We're in the middle of X, next step is Y."
5. Ask if the plan is still correct before doing anything.
6. If `_Updated` is more than 3 days old, flag it and ask the user to
confirm current state.
### Session end / pause / switch
1. Update `STATUS.md`: set the current task to 🟡, refresh "Where I stopped"
and "Next action".
2. Append non-obvious decisions to `<task-slug>.md` Decisions log.
3. Move finished items to "Completed steps".
4. Commit: `git add .tasks/ && git commit -m "chore: update task status [<task-slug>]"`.
### Task switch
1. Run session-end ops for the current task.
2. Read the target `<task-slug>.md`.
3. Set the target to 🔴 in `STATUS.md` (demote previous active to 🟡).
4. Confirm orientation before starting work.
### New task
1. Ask: slug, goal, known key files, branch.
2. Create `<task-slug>.md` with Goal and Key files populated.
3. Add a ⚪ block to `STATUS.md`.
4. Create / checkout the branch if missing.
### Task completion
1. **Pre-close coverage check** — list acceptance criteria, locate
evidence (tests, smoke-test artefacts, manual checklist ticks, design
doc refs). Missing evidence → ask the user before closing; never auto-close.
2. Resolve or drop all open questions.
3. Set status to 🟢 in `STATUS.md`.
4. Append a final summary line to the Decisions log.
5. Remind the user to delete the branch after merge.
### Post-commit task closure prompt
After a `feat:` / `fix:` commit the agent prompts:
"эта работа закрывает таску `<slug>`?". Slug candidates: commit-message
scope, current branch, most recent `Where I stopped`. If yes → run the
coverage check above. Skips `chore:` / `meta:` / `docs:` commits.
Forces a fresh-while-fresh decision, instead of letting shipped code sit
under a stale ⚪ block.
### Recommendations / "what's next" trigger
When the user asks «что дальше», «срочные», «куда копаем», "what next",
"status", or on session-start — recommend in this order:
1. **Local cwd-project board** ranked 🔴 → 🟡 → ⚪. Cite slugs.
2. **One footnote line** if relevant: `Cross-project: N 🔴 in other repos
(см. mcp__projects-meta__tasks_aggregate).` Only if N>0 and no local 🔴.
Explicit "по всем проектам" / "across all projects" flips the order.
Pairs with `using-projects-meta`'s local-first rule (which covers reads;
this one covers recommendations).
## Rules
- **Never lose "Where I stopped".** Most critical field. If unclear, ask
before ending the session.
- **One sentence per `STATUS.md` field.** Compress, don't write prose.
- **Key files must be specific** — not "auth module" but
`packages/auth/src/useAuth.ts:87`.
- **Decisions log is append-only.** Past entries are immutable.
- **Commit after every session end.** `git log` is the history of thinking.
- **Always confirm orientation at session start.** State understanding
before acting.
- **One active task at a time** — only one 🔴 in `STATUS.md`.
- **Never close without coverage check.** See "### Task completion"
step 1.
- **Local-first recommendations.** cwd-project first; cross-project at
most one footnote line.
## Install
From the repo root:
```bash
bash scripts/install.sh using-tasks
```
Works on Windows under git-bash, Linux, macOS.
## See also
- [`setup-tasks`](../setup-tasks/) — companion, owns `.tasks/` creation and
canon migration.
- [`project-bootstrap`](../project-bootstrap/) — invokes `setup-tasks` for
new projects.

View File

@@ -1,251 +0,0 @@
---
name: using-tasks
version: 1.4.0
description: >
Policy skill for working with an existing `.tasks/` board (per-task files + STATUS.md).
Use whenever the user is switching between tasks, resuming a paused task, starting a new
task, asking "where were we", says "use task management system", "pause", "switch to X",
"what's the status", "update status", or wants to track progress across parallel workstreams.
Trigger on any context-switching or multi-task coordination question in a code project.
If `.tasks/` is missing or non-canonical (no per-task `<task-slug>.md` files, no emoji
status legend in STATUS.md), delegate to `setup-tasks` first — it has its own confirmation
gate. Renamed from `task-status-wiki` at v1.0.0.
---
# using-tasks
> Policy for maintaining compressed working context across parallel tasks in a monorepo.
> The agent reads and updates `.tasks/` so every session starts oriented and every switch
> costs seconds, not minutes. This skill governs *usage* of an existing `.tasks/` — initial
> creation and migration to canon are owned by `setup-tasks`.
## Prerequisites
This skill assumes the project has a canonical `.tasks/` layout:
- `.tasks/STATUS.md` — the board, with per-task blocks using emoji status (🔴 active / 🟡 paused / ⚪ ready / 🟢 done / 🔵 blocked).
- `.tasks/<task-slug>.md` — one deep-context file per active or paused task.
If `.tasks/` is **missing**, or `STATUS.md` exists but is non-canonical (e.g. flat sections like "## Done" / "## In Progress" without the emoji + per-task block format, or no per-task files exist alongside STATUS.md) — invoke `setup-tasks` first. It detects greenfield vs migrate, has its own confirmation gate, and creates / migrates the structure. Only after `setup-tasks` finishes should this skill operate on `.tasks/`.
## Structure
```
<monorepo-root>/
.tasks/
STATUS.md ← active board: 🔴 / 🟡 / ⚪ / 🔵 blocks, sorted by priority
<task-slug>.md ← deep context per task, one file each
.lock ← runtime session lock; **gitignored** (never committed)
archive/
YYYY-MM.md ← 🟢 done blocks moved off the board, one file per month
```
Commit `.tasks/` to git. Decision history is valuable; diffs show how thinking evolved.
`STATUS.md` is the **active** board — it must stay lean so orientation reads stay cheap. Closed 🟢 tasks are archived to `archive/YYYY-MM.md` once they pile up; see "### Archiving done tasks".
> **`.tasks/.lock` must be listed in `.gitignore`** (add `.tasks/.lock` to your project's `.gitignore`). The lock file is ephemeral runtime state, not project history — it must never be committed.
---
## STATUS.md format
```markdown
# Task Board
_Updated: YYYY-MM-DD_
## 🔴 [task-slug] — short description
**Status:** active | paused | blocked | done
**Where I stopped:** one sentence — the exact thought or action interrupted
**Next action:** one concrete step to resume immediately
**Blocker:** (only if blocked) what is preventing progress
**Session break:** (optional) `true` — or a hint string for the next track. Marks this task as a session boundary.
**Branch:** git branch name
---
```
**Emoji convention:**
- 🔴 Active — currently worked on (only one at a time)
- 🟡 Paused — in progress, resumable
- ⚪ Ready — not started, fully defined
- 🟢 Done — completed; kept on the board until merged, then archived (see "### Archiving done tasks")
- 🔵 Blocked — waiting on external input
### `session_break` marker
A task may carry a `session_break` marker — set by whoever defines the task (e.g. the delegating workshop) when its completion is a natural place to stop and start a fresh session. It signals an autonomous agent: *finish this task, then pause instead of immediately claiming the next one.*
- **Type:** boolean or string.
- `session_break: true` — pause after close; the next track is "see STATUS.md".
- `session_break: "<hint>"` — pause after close; `<hint>` names the recommended next track.
- **Where it lives:** in the task's frontmatter when delivered via the task system (`session_break: true` / `session_break: "<hint>"`); mirrored on the local board as the optional `**Session break:**` field in the task's STATUS.md block.
- **Absent →** behaviour is unchanged: close the task and continue as usual.
The check is enforced in the **Task completion** flow below (after close, before claiming the next task).
---
## Per-task file format (`<task-slug>.md`)
```markdown
# <task-slug>
## Goal
One paragraph. What this achieves and why it matters in the monorepo.
## Key files
- `path/to/file.ts` — role in this task
- `path/to/other.ts:42` — specific line if relevant
## Decisions log
Reverse-chronological. Append only — never rewrite past entries.
- YYYY-MM-DD: Why X was chosen over Y
- YYYY-MM-DD: Constraint Z discovered, approach adjusted
## Open questions
- [ ] unresolved design or dependency questions
## Completed steps
- [x] steps finished this or previous sessions
## Notes
Temporary hypotheses, links, names of people to consult.
```
---
## Agent operations
### Session start
1. **Session lock guard.** If `.tasks/` exists, read `.tasks/.lock`.
- **Active agent lock** — `type:"agent"` with `heartbeat` ≤ 10 minutes old: print the hard warning below and **require explicit user confirmation** before proceeding. Do not touch the board until the user confirms.
```
⚠️ поллер ведёт <slug> — нельзя работать параллельно
```
(Substitute the `slug` field from the lock file if present, otherwise omit it.)
- **Stale lock** — any type whose TTL has expired (`type:"agent"` with `heartbeat` > 10 min ago; `type:"interactive"` with `started_at` > 2 h ago): silently overwrite.
- **Absent or stale lock** (including after user confirmation): write `.tasks/.lock`:
```json
{"type":"interactive","started_at":"<ISO8601>","ttl_minutes":120}
```
2. Check if `.tasks/STATUS.md` exists. If not → invoke `setup-tasks` and stop here until it returns.
3. Read `STATUS.md` — this is the orientation read (see note below on why it's a local read, not an MCP call).
4. If user names a task, read its `<task-slug>.md`.
5. Confirm in one sentence: "We're in the middle of X, next step is Y."
6. Ask if the plan is still correct before doing anything.
7. If STATUS.md `_Updated` date is >3 days ago, flag it and ask user to confirm current state.
8. If `STATUS.md` holds **≥ 10** 🟢 done blocks, archive them first (see "### Archiving done tasks") so the board you orient on is lean.
> **Orient by reading the local `STATUS.md`, not an MCP call.** It is the live board and — kept lean by archival — cheap to read. Do **not** reach for projects-meta tools to enumerate the current project's board:
> - `tasks_aggregate` is cache-based, cross-project, and does **not** index ready/done — its own docs say to read `.tasks/STATUS.md` directly for the current project.
> - `tasks_get_status(target_project, slug)` returns a **single** task's live status (`{status, found}`) by a slug you already know — it cannot list the board. Use it only to check **one** known task (e.g. confirm a delegated task's board state, or detect async-human parking), never for orientation.
### Session end / pause / switch
1. **Release session lock.** If `.tasks/.lock` exists and contains `"type":"interactive"`: delete `.tasks/.lock`. (Stale interactive locks are cleaned up here too; silently delete any interactive lock regardless of TTL.)
2. Update `STATUS.md`: set current task to 🟡, update "Where I stopped" and "Next action".
3. Append to `<task-slug>.md` Decisions log any non-obvious choices made this session.
4. Move finished items to "Completed steps".
5. Commit: `git add .tasks/ && git commit -m "chore: update task status [<task-slug>]"`
### Task switch
1. Perform session-end operations for the current task.
2. Read the target `<task-slug>.md`.
3. Set it to 🔴 in STATUS.md (demote previous active to 🟡).
4. Confirm orientation before starting work.
### New task creation
1. Ask: task name (slug), goal, known key files, branch name.
2. Create `<task-slug>.md` with Goal and Key files populated.
3. Add ⚪ block to `STATUS.md`.
4. Create and checkout branch if it doesn't exist.
### Task completion
1. **Pre-close coverage check.** Before setting 🟢:
- List acceptance criteria from the per-task `<slug>.md` (or the STATUS block if no per-task file).
- For each criterion, locate evidence: a test name in the diff, a smoke-test artefact, a manual-checklist tick in the per-task file, or a design-doc reference.
- Missing evidence on any criterion → flag to user and ask "закрывать или подождать coverage'а?". Never silently close.
- If acceptance criteria are policy / docs-only and have no testable shape, an explicit user "ok, closed by inspection" is required (record this in the close-note).
2. Resolve or drop all open questions.
3. Set status to 🟢 in STATUS.md.
4. Append final summary line to Decisions log.
5. Remind user to delete the branch after merge.
6. **Session-break check (after close, before claiming the next task).** Once the task is 🟢 and committed — and **before** any `tasks_claim_next` or starting the next task — read the closed task's `session_break` marker (its frontmatter `session_break`, or the `**Session break:**` field in its STATUS.md block). If present:
- Print this line **verbatim**, substituting the closed task's slug for `[slug]` and the marker's string value for `[value | "см. STATUS.md"]` (use the literal `см. STATUS.md` when the marker is just `true`):
`🔚 SESSION BOUNDARY — [slug] закрыта. Рекомендую завершить текущую сессию. Следующий трек: [value | "см. STATUS.md"]`
- **Stop.** Do not claim or start the next task.
- If the marker is absent → behaviour is unchanged: proceed to claim / start the next task as usual.
7. **Archival check.** After the close is committed, if `STATUS.md` now holds **≥ 10** 🟢 done blocks, archive them (see "### Archiving done tasks"). This keeps the board lean for the next orientation read.
### Archiving done tasks
🟢 done blocks accumulate in `STATUS.md` and bloat it — and since orientation reads the whole board, a bloated file burns context on every session start (the recurring "huge STATUS.md" complaint). Keep the board lean: done blocks stay only until merged, then move to a monthly archive.
**Threshold.** When `STATUS.md` holds **≥ 10** 🟢 done blocks, archive them. Check at two moments: (a) right after closing a task (Task completion step 7), and (b) at session start, before orienting (Session start step 7). The threshold is a ceiling, not a target — archive in batches; don't churn one block at a time.
**Where.** Append the archived blocks to `.tasks/archive/YYYY-MM.md` — one file per calendar month, keyed by the date of archival. Create `.tasks/archive/` and the month file if absent. If the month file already exists, **append**; never overwrite.
**Archive file format** (header written once, on file creation):
```markdown
# Archived done tasks — YYYY-MM
Moved out of `.tasks/STATUS.md` to keep the active board lean.
Full source is git history; this file is for grep-able historical context.
---
```
…followed by each 🟢 block **verbatim** (including its trailing `---` separator and any `<!-- closed-by … -->` comments).
**After archiving,** `STATUS.md` keeps only 🔴 / 🟡 / ⚪ / 🔵 blocks. Commit the move on its own:
```
git add .tasks/ && git commit -m "meta(tasks): archive done batch → .tasks/archive/YYYY-MM.md"
```
Leave a just-closed 🟢 block on the board only while it's still useful at a glance (pending merge, fresh reference). Everything older goes to the archive.
### Post-commit task closure prompt
After any implementation commit (`feat:` / `fix:` / similar), prompt the user once:
> Эта работа закрывает таску `<slug>`?
Slug candidates, in priority: (a) commit message scope, (b) current branch name, (c) the most recent `Where I stopped` field that mentions a now-shipped artefact. If user says yes → run the pre-close coverage check from "### Task completion". If no → silent.
Skip on `chore:` / `meta:` / `docs:` / `style:` commits — they rarely close work.
This exists because shipped code can sit while the task block stays ⚪ ready (e.g. `extend-project-discipline-brainstorm-workspaces` lived as ⚪ for a day after `215afdd` shipped Rule 5). The prompt forces a one-line decision while the work is fresh.
### Recommendations / "what's next" trigger
When the user asks «что дальше», «срочные», «куда копаем», «status», «what next», or session-start lands on a project — recommend in this order:
1. **Local cwd-project board** ranked 🔴 → 🟡 → ⚪. Group by status, summarize one line each. Cite slugs.
2. **One footnote line** if cross-project state is relevant: `Cross-project: N 🔴 active in other repos (см. mcp__projects-meta__tasks_aggregate).` Only when N>0 and there is no active 🔴 in the current cwd. Never bury local recommendations under it.
Cross-project urgents are *information*, not the driver of "what to do here". The user chose this cwd; that's the implicit scope.
If the user explicitly asks "across all projects" / "по всем проектам" / "cross-project status" — flip the order: cross-project first, local as footnote.
Pair: `using-projects-meta` declares local-first for **reads**; this rule extends local-first to the **recommendation phase**.
---
## Rules
- **Honour `.tasks/.lock`** — read the lock at session start before touching the board; write it after clearing the guard; delete it at session end/pause. Never skip the lock check when `.tasks/` exists. The lock file must be gitignored.
- **Never lose "Where I stopped"** — most critical field. If unclear, ask before ending session.
- **One sentence per STATUS.md field** — compress, don't write prose.
- **Key files must be specific** — not "auth module" but `packages/auth/src/useAuth.ts:87`.
- **Decisions log is append-only** — past entries are immutable.
- **Commit after every session end** — git log is the history of thinking.
- **Always confirm orientation at session start** — state understanding before acting.
- **One active task at a time** — only one 🔴 in STATUS.md.
- **Keep the board lean** — orientation reads the local `STATUS.md` whole, so archive 🟢 done blocks to `.tasks/archive/YYYY-MM.md` once ≥10 pile up. Never enumerate the current project's board via `tasks_aggregate` (cross-project cache) or `tasks_get_status` (single-task, by slug). See "### Archiving done tasks".
- **Never close a task without a coverage check** — see "### Task completion" step 1. Acceptance criteria with no evidence → ask, don't auto-close.
- **Honour `session_break`** — a closed task carrying a `session_break` marker means stop after close; never chain into `tasks_claim_next`. See "### Task completion" step 6.
- **Local-first recommendations** — cwd-project board comes first; cross-project urgents are at most one footnote line.

View File

@@ -1,182 +0,0 @@
# using-wiki
Runtime policy for an LLM Wiki built on the
[Karpathy LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).
Knowledge is **compiled once and kept current** across three layers, via
three named operations, with strict file formats that keep the wiki
parseable and grep-friendly.
`using-wiki` governs *usage* of an existing `.wiki/`. Initial creation and
migration to canon are owned by [`setup-wiki`](../setup-wiki/).
> Renamed from `wiki-maintainer` at v1.0.0.
## When it triggers
- User says: "use project wiki", "query the wiki", "ingest this", or the
Russian equivalents ("обнови вики", "проверь вики", "запроси вики",
"заингесть").
- Any time the agent modifies a file under `.wiki/` — the workflow and
formats below are mandatory.
- If `.wiki/` is missing or non-canonical, this skill delegates to
[`setup-wiki`](../setup-wiki/) before doing anything else.
## Three layers (do not blur)
1. **Raw sources** — `.wiki/raw/` (or external paths registered in
`raw/README.md`). **Immutable.** Read, never edit. The only exception is
appending a `> Status` blockquote when the user explicitly asks for a
status audit.
2. **Wiki** — everything else under `.wiki/`. Agent-owned. Entity / concept /
package / source summary pages.
3. **Schema** — `.wiki/CLAUDE.md`. Project-specific conventions (what
entities, what packages, naming). Always read it first; it overrides this
skill on conflict.
## Three operations
### Ingest
«заингесть X» — pull a raw source into the wiki.
1. Read the raw source fully.
2. Extract: entities, concepts, packages, cross-cutting patterns.
3. Create `sources/<slug>.md` (one summary page per source, ~50–150 lines).
4. For each affected entity / concept / package page: update if exists,
create if not. Flag contradictions explicitly with
`> **Противоречие:** источник A говорит X, источник B — Y`.
**Never silently overwrite.**
5. Update `index.md`.
6. Append one line to `log.md`.
7. Report: what was created, updated, contradicted.
One ingest may touch 10–15 pages. That's normal — that's why an LLM does it.
### Query
A question answered from the wiki.
1. Read `index.md` first, drill into relevant pages.
2. Answer with citations as markdown links.
3. **Compound the wiki.** If the answer is a real synthesis, ask the user:
"Сохранить как страницу wiki?" Good queries become durable pages under
`concepts/` or `analyses/`.
4. Append one line to `log.md`.
### Lint
«проверь wiki» — health check.
Scan for:
- Contradictions between pages.
- Orphans (pages with no inbound links).
- Stale claims (raw source updated after the summary's `ingested:` date —
check via `git log -p`).
- Concepts mentioned in prose but missing their own page.
- Empty / TODO sections.
Report as a punch list. Don't delete anything automatically. Append one
line to `log.md` with the findings.
## File formats (mandatory)
### Page frontmatter
```yaml
---
title: Человекочитаемое имя
type: entity | concept | package | source | contradiction | open-question | overview
tags: [short, tokens]
sources: [../sources/foo.md, ../sources/bar.md]
updated: 2026-04-21
---
```
Source pages also carry `ingested: YYYY-MM-DD` and `raw_path: ../raw/...`.
Contradiction pages also carry `status: open | resolved | accepted-divergence` and `affects: [../entities/x.md, ../concepts/y.md]`.
Open-question pages also carry `status: open | answered | obsolete` and `touches: [../entities/x.md, ../sources/z.md]`.
### File naming
- `kebab-case.md`, **Latin only**. Transliterate Cyrillic / non-Latin in
filenames; keep the original title in H1 + frontmatter.
- `entities/<name>.md`, `concepts/<name>.md`, `packages/<name>.md`
(no `@org/` prefix), `sources/<slug>.md`, `contradictions/<slug>.md`,
`open-questions/<slug>.md`.
### `log.md` — append-only, grep-parseable
Every entry must start with:
```
## [YYYY-MM-DD] <operation> | <short description>
```
Operations: `ingest`, `query`, `lint`, `refactor`, `decision`, `init`.
Parse with: `grep "^## \[" .wiki/log.md | tail -20`.
### `index.md`
Catalog, not narrative. One line per page: `- [Title](path) — hook.`
Sections by type. Update on every ingest.
### Cross-references
- Wiki → wiki: relative markdown links — `[Name](../entities/x.md)`.
- Wiki → code: relative path from repo root — `[foo.js](../../packages/api/foo.js)`.
- Wiki → raw: `../raw/<file>`.
- URL-encode spaces (`%20`) and Cyrillic when needed.
## Quick reference
| Situation | Files touched |
|---|---|
| Ingest one doc | `sources/<slug>.md` (new) + 3–15 entity/concept/package pages + `index.md` + `log.md` |
| Query | (read only) + optionally a new wiki page + `log.md` |
| Lint | (read only) + `log.md` |
| Bootstrap / migrate | (delegated to [`setup-wiki`](../setup-wiki/)) |
## Common mistakes
- **Editing `raw/`.** Don't. Only allowed change: status blockquote on
explicit request.
- **Dumping raw content into `sources/`.** Summaries are summaries. Link to
raw, don't copy.
- **Silent overwrites on contradictions.** Flag them with a `> **Противоречие:**`
block.
- **Narrative `log.md`.** "Today I added…" is wrong. Use
`## [YYYY-MM-DD] ingest | <what>`.
- **Non-ASCII filenames.** Breaks greppability and cross-platform. Transliterate.
- **Forgetting `index.md`.** Pages not listed there are invisible to future
queries.
- **Improvising layout when canon files are missing.** Hand off to
[`setup-wiki`](../setup-wiki/) instead of patching ad-hoc.
## When NOT to use
- The project has CLAUDE.md / AGENTS.md docs but no `.wiki/` — that's regular
documentation, not an LLM Wiki.
- The user wants a single-file README or ADR — this skill is for persistent,
interlinked knowledge bases.
- One-off questions about code — read files directly, no wiki workflow needed.
## Install
From the repo root:
```bash
bash scripts/install.sh using-wiki
```
Works on Windows under git-bash, Linux, macOS.
## See also
- [`setup-wiki`](../setup-wiki/) — companion, owns `.wiki/` creation and
canon migration.
- [`project-bootstrap`](../project-bootstrap/) — invokes `setup-wiki` for
new projects.
- Karpathy's LLM Wiki gist:
<https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f>

View File

@@ -1,138 +0,0 @@
---
name: using-wiki
version: 1.1.0
description: Policy skill for working with an existing `.wiki/` (Karpathy LLM Wiki pattern). Use when the user asks to ingest a document, answer from the wiki, lint/health-check it, or says "use project wiki", "обнови вики", "проверь вики", "запроси вики", "заингесть", "query the wiki". Also use when modifying any file under `.wiki/` — the workflow and formats below are mandatory, and project-specific conventions live in `.wiki/CLAUDE.md`. If `.wiki/` is missing or non-canonical, delegate to `setup-wiki` first (it has its own confirmation gate). Renamed from `wiki-maintainer` at v1.0.0.
---
# using-wiki
> Policy for maintaining an LLM Wiki (Karpathy pattern: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f). Knowledge is **compiled once and kept current** across three layers, via three named operations, with strict file formats that make the wiki parseable and grep-friendly. This skill governs *usage* of an existing wiki — initial creation and migration to canon are owned by `setup-wiki`.
## Prerequisites
This skill assumes the project has a canonical `.wiki/` layout: `CLAUDE.md` (schema), `index.md` (catalog), `log.md` (op log), `overview.md`, `raw/README.md`, and the six content directories `entities/`, `concepts/`, `packages/`, `sources/`, `contradictions/`, `open-questions/`.
If `.wiki/` is **missing**, or the layout is **non-canonical** (e.g. `SUMMARY.md` instead of `index.md`, or `source/` instead of `concepts/`/`sources/`, or `contradictions/`/`open-questions/` directories are absent) — invoke the `setup-wiki` skill first. It detects the situation (greenfield vs migrate) and creates or migrates the structure with its own confirmation gate. Only after `setup-wiki` finishes should this skill proceed with the operations below.
## Three layers (do not blur)
1. **Raw sources** — `.wiki/raw/` (or external paths registered in `raw/README.md`). **Immutable.** Read, never edit. The only exception is appending a `> Status` blockquote when the user explicitly asks for a status audit.
2. **Wiki** — everything else under `.wiki/`. Agent-owned. Entity / concept / package / source summary pages.
3. **Schema** — `.wiki/CLAUDE.md`. Project-specific conventions (what entities, what packages, naming). Always read it first if present; it overrides this skill when it conflicts.
## First step on every operation
1. Read `.wiki/CLAUDE.md` if it exists.
2. Read `.wiki/index.md` to locate relevant pages.
3. Only then act.
If `.wiki/CLAUDE.md` is missing, the layout is incomplete — invoke `setup-wiki` rather than improvising.
## Three operations
### Ingest — «заингесть X»
1. Read the raw source fully.
2. Extract: entities, concepts, packages, cross-cutting patterns.
3. Create `sources/<slug>.md` (one summary page per source, ~50–150 lines).
4. For each affected entity/concept/package page:
- If it exists → update it. **Flag contradictions explicitly** with `> **Противоречие:** источник A говорит X, источник B — Y`. Don't silently overwrite.
- If not → create it.
5. Update `index.md` — add or move entries.
6. Append one line to `log.md` (format below).
7. Report to the user: what created, what updated, what contradictions found.
**One ingest may touch 10–15 pages. This is normal — that's why LLMs do it.**
### Query — вопрос по wiki
1. Read `index.md` first, then drill into relevant pages.
2. Answer with citations as markdown links to wiki pages.
3. **Compound the wiki.** If the answer is a real synthesis (comparison, analysis, new connection) — ask the user: "Сохранить как страницу wiki?" Good queries become durable pages under `concepts/`, `analyses/`, or similar.
4. Append one line to `log.md`.
### Lint — «проверь wiki»
Scan for:
- **Contradictions** between pages.
- **Orphans** — pages with no inbound links.
- **Stale claims** — git `log -p` on the raw source shows it was updated after the summary's `ingested:` date.
- **Missing entities** — concepts mentioned in prose but without their own page.
- **Empty/TODO sections.**
Report as a punch list. Don't delete anything automatically.
Append one line to `log.md` summarizing the findings.
## File formats (MANDATORY)
### Page frontmatter
```yaml
---
title: Человекочитаемое имя
type: entity | concept | package | source | contradiction | open-question | overview
tags: [short, tokens]
sources: [../sources/foo.md, ../sources/bar.md]
updated: 2026-04-21
---
```
Source pages also carry `ingested: YYYY-MM-DD` and `raw_path: ../raw/...`.
Contradiction pages also carry `status: open | resolved | accepted-divergence` and `affects: [../entities/x.md, ../concepts/y.md]`.
Open-question pages also carry `status: open | answered | obsolete` and `touches: [../entities/x.md, ../sources/z.md]`.
### File naming
- `kebab-case.md`, **Latin only**. Transliterate Cyrillic / other scripts in filenames (`план переписывания` → `ozon-client-rewrite.md`). Keep the original title in the H1 and frontmatter.
- `entities/<name>.md`, `concepts/<name>.md`, `packages/<name>.md` (no `@org/` prefix), `sources/<slug>.md`, `contradictions/<slug>.md`, `open-questions/<slug>.md`.
### `log.md` — append-only, grep-parseable
Every entry **must** start with:
```
## [YYYY-MM-DD] <operation> | <short description>
```
Operations: `ingest`, `query`, `lint`, `refactor`, `decision`, `init`.
Parseable with: `grep "^## \[" .wiki/log.md | tail -20`.
### `index.md`
Catalog, not narrative. One line per page: `- [Title](path) — hook.` Sections by type (entities / concepts / packages / sources / contradictions / open-questions). Update on every ingest.
### Cross-references
- Wiki → wiki: relative markdown links, `[Name](../entities/x.md)`.
- Wiki → code: relative path from repo root: `[foo.js](../../packages/api/foo.js)`.
- Wiki → raw: `../raw/<file>`.
- URL-encode spaces in paths (`%20`) and Cyrillic when needed.
## Quick reference
| Situation | Files touched |
|---|---|
| Ingest one doc | `sources/<slug>.md` (new) + 3–15 entity/concept/package pages + `index.md` + `log.md` |
| Query | (read only) + optionally new wiki page + `log.md` |
| Lint | (read only) + `log.md` |
| Bootstrap / migrate to canon | (delegated to `setup-wiki`) |
## Common mistakes
- **Editing `raw/`.** Don't. Only allowed: status blockquote when user explicitly asks.
- **Dumping raw content into `sources/`.** Summaries are summaries. Link to raw, don't copy it.
- **Silent overwrites.** When a new source contradicts an existing page, flag it with a `> **Противоречие:**` block; don't just overwrite.
- **Narrative `log.md`.** `Today I added…` is wrong. Use `## [YYYY-MM-DD] ingest | <what>`.
- **Non-ASCII file names.** Breaks greppability and cross-platform. Transliterate.
- **Forgetting `index.md`.** Pages not listed there are effectively invisible for future queries.
- **Skipping contradictions in lint.** The wiki's value grows from surfaced tensions, not from false consensus.
- **Improvising layout when canon files are missing.** If the wiki is missing or partial, hand off to `setup-wiki` instead of patching ad hoc.
## When NOT to use this skill
- Project has CLAUDE.md / AGENTS.md docs but no `.wiki/` — that's regular project documentation, not an LLM Wiki.
- User wants a single-file README or ADR — this skill is for persistent interlinked knowledge bases.
- One-off questions about code — use regular file reading, not wiki workflow.

View File

@@ -1,29 +0,0 @@
# pulling-before-work
Policy skill that pulls the current branch from `origin` once at session start
and on explicit re-sync requests. Designed to remove the "edited on stale base"
footgun without trampling dirty work-trees or auto-merging.
## When it triggers
- **Session start** — when `CLAUDE.md` contains the line `pull remote before work` (added by `project-bootstrap` v1.4.0+).
- **In-chat** — when the user says `sync`, `resync`, `pull`, `обнови репо`, `git pull please`, or close variants.
Stays silent in non-git folders. Prints one informational line and exits in:
no `origin` remote, no upstream tracking, dirty work-tree, detached HEAD.
## What it does
`git pull --ff-only` against the configured upstream — never auto-merges, never
auto-rebases, never stashes, never commits, never pushes. On divergence it prints
a warning with manual-resolution hints and exits.
## Prerequisites
None. The skill is a no-op outside git repos and folders without an `origin`
remote, so it's safe to leave activated everywhere.
## Related
- `project-bootstrap` (v1.4.0+) — adds the trigger line to new and existing projects' `CLAUDE.md`.
- `.wiki/concepts/pulling-before-work-design.md` (in projects bootstrapped from this repo: this design lives in `claude-skills`) — full design rationale.

View File

@@ -1,153 +0,0 @@
---
name: pulling-before-work
version: 1.0.0
description: >
Pulls the current branch from origin once at session start and on explicit
re-sync requests. Use when CLAUDE.md contains the trigger line "pull remote
before work", or when the user says "sync", "resync", "pull", "обнови репо",
"git pull please", or close variants asking to refresh from the remote.
Runs `git pull --ff-only` — never auto-merges or rebases. Stays silent in
non-git folders. Prints one informational line and exits when there is no
origin remote, no upstream tracking, the working tree is dirty, or HEAD is
detached. Does not stash, commit, or push. Activated by `project-bootstrap`
v1.4.0+ via the canonical CLAUDE.md template.
---
# pulling-before-work
> Pull from `origin` once when work starts. Don't auto-merge. Don't trample dirty work-trees. Don't ask twice in the same session unless asked.
## When this runs
**At session start** — once, when the skill is activated by the `pull remote before work` line in `CLAUDE.md`. The cycle below runs immediately.
**On explicit re-sync** — when the user says any of: `sync`, `resync`, `pull`, `обнови репо`, `pull please`, `git pull`, `подтяни`, `pull from origin`. Re-runs the full cycle. There is no per-session counter; the user is always allowed to ask.
**Never** before each commit, before each tool call, on every message, or in any other implicit cadence. Mode-3 ("start + on-demand") was the explicit design choice — see `.wiki/concepts/pulling-before-work-design.md`.
## The pull cycle
Run these checks in order. Print at most one line of chat output per run.
### 1. Inside a git work-tree?
```bash
git rev-parse --is-inside-work-tree 2>/dev/null
```
If the command fails or prints anything other than `true` → **exit silently, no chat output.** This is the not-a-git-repo case; the skill must not be noisy in random folders.
### 2. Has an `origin` remote?
```bash
git remote get-url origin 2>/dev/null
```
If the command fails (no such remote) → print one line and exit:
```
no origin remote — skip pull
```
### 3. Is the working tree clean?
```bash
git status --porcelain
```
If the output is non-empty → print one line and exit:
```
working tree dirty — skipping pull. commit/stash, потом скажи "sync"
```
Never stash automatically. Stash-pop conflicts are exactly the friction this skill exists to remove.
### 4. Is HEAD attached?
```bash
git symbolic-ref -q HEAD
```
If the command fails (empty output, exit 1) → detached HEAD. Print:
```
detached HEAD — skip pull
```
### 5. Does the current branch have an upstream?
```bash
git rev-parse --abbrev-ref --symbolic-full-name '@{u}' 2>/dev/null
```
Capture the upstream name (e.g. `origin/master`). If the command fails → no upstream tracking. Print:
```
no upstream tracking for <branch> — skip pull
```
(Where `<branch>` is `git rev-parse --abbrev-ref HEAD`.)
### 6. Pull, fast-forward only
```bash
git pull --ff-only
```
(No args — uses the configured upstream captured above.)
Classify by exit code and stdout:
| Result | Print |
|---|---|
| Already up to date | `✅ already up to date with <upstream>` |
| Fast-forward, N commits | `✅ pulled N commits from <upstream>` |
| Non-fast-forward / diverged (exit non-zero with "diverged" or "non-fast-forward" in output) | `⚠️ diverged from <upstream> — resolve manually (git pull --rebase or merge); skill never auto-merges/rebases` |
### Out of scope
The skill never:
- commits, stashes, or pushes
- recurses into submodules
- pulls from non-`origin` remotes
- pulls on detached HEAD
- runs auto-merge or auto-rebase
- runs more than once per session unless the user asks
## Recovery hints
If the skill skipped because of a dirty tree:
```powershell
# Windows / PowerShell
git status # see what's dirty
git add . ; git commit -m "wip"
# then ask the agent: "sync"
```
```bash
# Linux / macOS
git status
git add . && git commit -m "wip"
# then say "sync"
```
If the skill reported `diverged`:
```bash
# Option A: rebase your local commits on top of origin
git pull --rebase
# Option B: explicit merge (creates a merge commit)
git pull --no-ff
```
The skill stays out of these decisions on purpose — both options have valid use cases and the user owns the choice.
## Why this exists
Stale local branches are a silent footgun: edits land on top of yesterday's `origin`, the divergence shows up at push time, and by then there's a chunk of work to rebase or merge on the wrong base. One pull at start covers the common case; an explicit re-sync trigger handles long sessions where someone pushed mid-flight.
Full design rationale (mode choice, dirty-tree skip vs stash, `--ff-only` vs auto-merge, the upstream-check) lives in `.wiki/concepts/pulling-before-work-design.md`.

BIN
dist/browser-cdp.skill vendored

Binary file not shown.

BIN
dist/browser-operator.skill vendored Normal file

Binary file not shown.

BIN
dist/code-search.skill vendored Normal file

Binary file not shown.

Binary file not shown.

Binary file not shown.

BIN
dist/mappa-vitya-brainstorming.skill vendored Normal file

Binary file not shown.

Binary file not shown.

BIN
dist/ops-browser.skill vendored Normal file

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

BIN
dist/task-format.skill vendored

Binary file not shown.

BIN
dist/task-loop.skill vendored

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

BIN
dist/using-tasks.skill vendored

Binary file not shown.

Binary file not shown.

BIN
dist/using-wiki.skill vendored

Binary file not shown.

Binary file not shown.

View File

@@ -36,10 +36,6 @@ skills:
# ─── auto (4 universals — MVP target) ──────────────────────────────── # ─── auto (4 universals — MVP target) ────────────────────────────────
pulling-before-work:
mode: auto
category: software-development
active-platform: active-platform:
mode: auto mode: auto
category: software-development category: software-development
@@ -59,6 +55,14 @@ skills:
mode: auto mode: auto
category: software-development category: software-development
browser-operator:
mode: auto
category: software-development
ops-browser:
mode: auto
category: software-development
using-markitdown: using-markitdown:
mode: auto mode: auto
category: productivity category: productivity
@@ -96,18 +100,10 @@ skills:
mode: auto mode: auto
category: productivity category: productivity
using-tasks:
mode: auto
category: productivity
setup-wiki: setup-wiki:
mode: auto mode: auto
category: research category: research
using-wiki:
mode: auto
category: research
setup-projects-meta: setup-projects-meta:
mode: manual mode: manual
source: hermes/skills/setup-projects-meta source: hermes/skills/setup-projects-meta
@@ -140,13 +136,6 @@ skills:
# ─── pending (8 — behavioral audit required) ───────────────────────── # ─── pending (8 — behavioral audit required) ─────────────────────────
delegate-task:
mode: pending
intended:
mode: auto
category: mcp
reason: "Calls mcp__projects-meta__tasks_create to create tasks in other projects/agents (Gitea commit, cross-project side-effect). Behavioral audit via delegate-task-test-trigger required before promotion to auto."
using-yt-tools: using-yt-tools:
mode: pending mode: pending
intended: intended:
@@ -161,20 +150,6 @@ skills:
category: mcp category: mcp
reason: "Calls mcp__vds-ops__* tools (read-only, but touches infrastructure). Behavioral audit via using-vds-ops-test-trigger required before promotion to auto." reason: "Calls mcp__vds-ops__* tools (read-only, but touches infrastructure). Behavioral audit via using-vds-ops-test-trigger required before promotion to auto."
using-wiki-graph:
mode: pending
intended:
mode: auto
category: mcp
reason: "Calls mcp__wiki-graph__* tools (read-only, parses a .wiki/ corpus server-side). Behavioral audit via using-wiki-graph-test-trigger required before promotion to auto."
session-handoff:
mode: pending
intended:
mode: auto
category: productivity
reason: "Writes .tasks/NEXT_SESSION.md (project-scope, sliding overwrite) and reads it on session start. Bidirectional file-system side-effect, opt-in via CLAUDE.md trigger-line. Behavioral audit via session-handoff-test-trigger required before promotion to auto."
private-dev-public-publish: private-dev-public-publish:
mode: pending mode: pending
intended: intended:
@@ -182,20 +157,6 @@ skills:
category: software-development category: software-development
reason: "Steps shell out to git / gh / Gitea-API, handle tokens, force-push, and repo deletion/privacy toggles — not a purely stylistic skill. Behavioral audit via private-dev-public-publish-test-trigger required before promotion to auto." reason: "Steps shell out to git / gh / Gitea-API, handle tokens, force-push, and repo deletion/privacy toggles — not a purely stylistic skill. Behavioral audit via private-dev-public-publish-test-trigger required before promotion to auto."
task-loop:
mode: pending
intended:
mode: auto
category: mcp
reason: "Orchestrates the board claim/close/update/heartbeat cycle via mcp__projects-meta__tasks_claim_next / tasks_close / tasks_update / tasks_heartbeat (cross-session claim ownership, irreversible close, Gitea side-effects) and may arm a single long ScheduleWakeup for the explicit long-watch opt-in. Critical-infra-adjacent — touches the same claim/close machinery the unattended poller relies on. Behavioral audit via task-loop-test-trigger required before promotion to auto."
session-inbox-monitor:
mode: pending
intended:
mode: auto
category: productivity
reason: "Paired SessionStart hook registers itself in ~/.claude/settings.json and sweeps orphaned monitor OS processes (Get-CimInstance | Stop-Process by sentinel+inbox-path); the skill then raises an in-session Monitor on .agents/inbox/. Primary activation is the CLAUDE.md trigger-line `inbox monitor: raise on start` + the injector, not a hermes-trigger. Behavioral gate CLEARED 2026-06-17 — test-trigger + review BOTH VERDICT PASS (activation 3/3 monitor + neg clean; structural hook audit 5 PASS/1 CONCERN, the CONCERN fixed in v0.2.2). STAYS pending on two independent tool-side blockers, NOT on behavioral verification: (1) the SessionStart hook is Windows-PowerShell and needs a Linux port for Hermes factory machines; (2) machine-level side-effects (user-config mutation of ~/.claude/settings.json + Get-CimInstance|Stop-Process kills) need a tool-side audit before auto. Promotion blocked on those two, not on test-trigger/review."
inter-session-peer-discipline: inter-session-peer-discipline:
mode: auto mode: auto
category: meta category: meta
@@ -220,20 +181,6 @@ skills:
category: meta category: meta
reason: "Resolves WHERE a project's meta lives before tasks_create / knowledge_ingest / brainstorm-promotion (meta-out-of-repo). Touches projects-meta MCP (tasks_create / knowledge_ingest / meta_status) and routes writes across repos. Review PASS (meta-host-routing-review) but the -install baseline is still open and a tool-side audit (cross-repo MCP writes) is required before auto. Mapping executes task meta-host-routing-hermes-mapping." reason: "Resolves WHERE a project's meta lives before tasks_create / knowledge_ingest / brainstorm-promotion (meta-out-of-repo). Touches projects-meta MCP (tasks_create / knowledge_ingest / meta_status) and routes writes across repos. Review PASS (meta-host-routing-review) but the -install baseline is still open and a tool-side audit (cross-repo MCP writes) is required before auto. Mapping executes task meta-host-routing-hermes-mapping."
using-system-snapshot:
mode: pending
intended:
mode: auto
category: mcp
reason: "Calls mcp__projects-meta__meta_system_snapshot (read-only whole-machine ops snapshot: poller / docker / cross-project task load). Read-only, same class as using-vds-ops / using-wiki-graph; pending a behavioral test-trigger before auto."
task-format:
mode: pending
intended:
mode: auto
category: productivity
reason: "Documentational skill — how to write a .tasks/STATUS.md task block the autonomous poller will claim/route/report (block header, status emoji, Weight/Notify/Requirements fields). No tool-side effects; pending a behavioral test-trigger before auto."
setup-agents-task-runner: setup-agents-task-runner:
mode: pending mode: pending
reason: "L2 installer — installs the standing-duty stack (agents-task-runner + watchdog + appeals-inbox) as platform-native OS services (systemd/launchd/winsw), fetches a pinned binary, writes poller-scope.json. Heavy infra side-effects (OS services + binary fetch); mode decision (skip vs manual vs auto) deferred — needs an explicit Hermes-factory applicability audit. Placeholder pending to keep the build green." reason: "L2 installer — installs the standing-duty stack (agents-task-runner + watchdog + appeals-inbox) as platform-native OS services (systemd/launchd/winsw), fetches a pinned binary, writes poller-scope.json. Heavy infra side-effects (OS services + binary fetch); mode decision (skip vs manual vs auto) deferred — needs an explicit Hermes-factory applicability audit. Placeholder pending to keep the build green."
@@ -241,3 +188,47 @@ skills:
ralph-loop-execution: ralph-loop-execution:
mode: pending mode: pending
reason: "Behavioral oracle-loop skill (Verifier / Attempts / Max-Attempts retry loop). NB: source SKILL.md currently lacks YAML frontmatter (no name/description) — cannot auto-convert cleanly until that is fixed. Mapped pending as a placeholder; needs frontmatter + a behavioral audit before any mode decision." reason: "Behavioral oracle-loop skill (Verifier / Attempts / Max-Attempts retry loop). NB: source SKILL.md currently lacks YAML frontmatter (no name/description) — cannot auto-convert cleanly until that is fixed. Mapped pending as a placeholder; needs frontmatter + a behavioral audit before any mode decision."
# ─── mappa-skill-suite (7, pending — behavioral audit via mappa-skill-suite-review) ───
mappa-messaging:
mode: pending
intended:
mode: auto
category: communication
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-knowledge:
mode: pending
intended:
mode: auto
category: research
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-brainstorm-promote:
mode: pending
intended:
mode: auto
category: meta
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-delegation:
mode: pending
intended:
mode: auto
category: mcp
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-task-work:
mode: pending
intended:
mode: auto
category: productivity
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-closing-ritual:
mode: pending
intended:
mode: auto
category: productivity
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."
mappa-session-orient:
mode: pending
intended:
mode: auto
category: productivity
reason: "Calls mcp__mappa__* tools (board/wiki/inbox/handoff/sessions). Behavioral audit via mappa-skill-suite-review required before promotion to auto."

View File

@@ -44,7 +44,7 @@ function New-SkillArchive {
[System.IO.Compression.ZipArchiveMode]::Create [System.IO.Compression.ZipArchiveMode]::Create
) )
try { try {
$files = Get-ChildItem -Path $sourceFull -Recurse -File $files = Get-ChildItem -Path $sourceFull -Recurse -File | Where-Object { $_.FullName -notmatch '__pycache__' }
foreach ($file in $files) { foreach ($file in $files) {
$rel = $file.FullName.Substring($sourceFull.Length + 1) -replace '\\','/' $rel = $file.FullName.Substring($sourceFull.Length + 1) -replace '\\','/'
$entryName = "$SkillName/$rel" $entryName = "$SkillName/$rel"

View File

@@ -1,13 +1,14 @@
--- ---
name: browser-cdp name: browser-cdp
author: ours author: ours
version: 0.1.0 version: 0.1.1
description: > description: >
Веб-автоматизация через минимальные CDP CLI-тулы в bash — вместо playwright-mcp Веб-автоматизация через минимальные CDP CLI-тулы в bash — вместо playwright-mcp
/ Chrome-DevTools-MCP (подход «what if you don't need MCP»). Запуск Chrome с remote / Chrome-DevTools-MCP (подход «what if you don't need MCP»). Запуск Chrome с remote
debugging, навигация, eval JS, скриншоты. Trigger: «браузер», «скрейпинг», «открой debugging, навигация, eval JS, скриншоты. Trigger: «браузер», «скрейпинг», «открой
страницу», «перейди на», «сделай скриншот», «playwright», «веб-автоматизация», страницу», «перейди на», «сделай скриншот», «playwright», «веб-автоматизация»,
«web scraping», «browser». «web scraping», «browser». Для ЛИЧНЫХ КАБИНЕТОВ оператора (его логины, антибот) —
НЕ этот скил, а `browser-operator`.
--- ---
# browser-cdp # browser-cdp
@@ -20,6 +21,9 @@ description: >
снять скриншот, собрать данные (скрейпинг). Использовать **вместо** playwright-mcp или снять скриншот, собрать данные (скрейпинг). Использовать **вместо** playwright-mcp или
Chrome-DevTools-MCP. Chrome-DevTools-MCP.
- ⚠️ **Для личных кабинетов оператора этот путь НЕ годится:** здесь свой Chrome и свой
профиль (без его логинов). Нужен браузер оператора — скил `browser-operator`.
## Процесс ## Процесс
1. **Прочитай полную справку** (обязательно, первый шаг): 1. **Прочитай полную справку** (обязательно, первый шаг):

View File

@@ -0,0 +1,128 @@
---
name: browser-operator
author: ours
version: 0.1.0
description: >
Работа в браузере ОПЕРАТОРА — его Chrome, его профиль, его живые логины: личные
кабинеты поставщиков (ЧипДип, ДКО, Промэлектроника, ТМ), Avito, порталы под
антиботом. Trigger: «зайди в личный кабинет», «открой ЛК», «собери заказы»,
«посмотри в браузере», «нужна его сессия», «ЧипДип/Ozon/Avito», «browser».
НЕ для публичных страниц (там сначала обычный fetch/curl) и НЕ для анонимных
прогонов (там скил browser-cdp).
---
# Browser operator — браузер оператора
**Браузер оператора — разделяемый ресурс с его живыми сессиями.** Работай через
готовый канал своего харнесса и **только под арендой «один водитель за раз»**.
Не вытаскивай его куки, не логинься сам, не поднимай свой Chrome.
## Когда браузер действительно нужен
Сначала спроси себя, нужен ли браузер вообще:
- **Нет** — публичная страница, API, доки: обычный fetch/curl/поиск. Браузер тут лишний.
- **Да** — страница требует взаимодействия (клик/форма/навигация), JS-рендер,
**его логин** (личный кабинет, Avito), либо портал режет не-браузерный трафик.
## Канал по харнессу (не изобретай свой)
| Харнесс | Чем работать | Аренда |
|---|---|---|
| **Hermes** | тул `browser_exec` (демон `browser-use`, тот же профиль оператора) | автоматически: shell-хук `pre_tool_call` берёт аренду и блокирует вызов при чужой |
| **pi** | тул `browser`: `open` / `read` / `js` / `click` / `screenshot` / `lease` | автоматически внутри тула; `lease` покажет, кто держит |
| **Claude Code** | MCP `chrome-devtools` (`list_pages`, `navigate_page`, `take_snapshot`, `evaluate_script`, `click`, `fill`, `take_screenshot`) | автоматически: обёртка берёт аренду перед стартом сервера |
**Никогда:** `curl` с куками из его профиля, `browser_cookie3`-выгрузка куки,
свой `chrome --remote-debugging-port` с пустым профилем (там нет его логинов),
`pip install`-стек ради одного кабинета.
## Аренда: «один водитель в браузере за раз»
Браузер один. Если его держит другой харнесс — **не ломиться**, сказать «занято,
держит X» и вернуться позже (или попросить оператора освободить).
Идёшь в браузер **в обход** тула (например, скриптом или `browser-use` из терминала) —
бери аренду сам:
```bash
BL="$HOME/.config/browser-harness/bin/browser-lease.sh"
HOLD="manual:$$" # метка держателя
MYPID="$(cat /proc/$$/winpid 2>/dev/null || echo 0)" # НАСТОЯЩИЙ windows-PID
bash "$BL" acquire --holder "$HOLD" --ttl 900 --pid "$MYPID" --tool browser # 0 = взял, 3 = занято, 2 = ошибка
# … работа …
bash "$BL" release --holder "$HOLD"
```
**PID — только настоящий.** MSYS `$$` это НЕ windows-PID: по нему живость аренды врёт
(мёртвый держатель выглядит живым, живой — мёртвым). В bash бери `/proc/$$/winpid`,
в pi/Node — `process.pid`; не знаешь — передай `0` («неизвестен», живость решит TTL).
**`driver.lock` руками не трогай** (в том числе пустой или «битый» — это окно чужой
записи): отбор мёртвой аренды делает CLI по `ts`/TTL/мёртвому PID. Чужую аренду не снимай.
Контракт аренды (формат файла, TTL, кого связывать): вики mappa
`concepts/browser-lease-contract`.
## Как работать в страницах (рецепты)
- **Первым делом — своя вкладка.** `ensure_real_tab()` / `new_tab(url)`; не полагайся
на активную вкладку оператора: тяжёлая или аудио-страница подвешивает демон
(все вызовы падают в таймаут, хотя `browser-use --doctor` говорит «alive»).
- **Тяжёлые страницы — читать изнутри, а не обходом.** Если у сайта есть внутренний
JSON-эндпоинт, зови его `fetch(path, {credentials:'include'})` из уже открытой
страницы: это быстрее и надёжнее десятков навигаций.
- **По одной штуке за раз, с паузами.** Паузы — в Python/процессе, **не** в JS `await`
(иначе `Runtime.evaluate timed out`). Ориентир оператора: 1 запрос, пауза 7–13 с,
перекур каждые ~40, стоп после 3 ошибок подряд.
- **Клики:** сначала дерево доступности (`Accessibility.getFullAXTree`) или
`querySelector` → центр элемента (`getBoundingClientRect`) → `click_at_xy` → **проверь
результат** отдельным `js(...)`/`page_info()`. Не кликай «на глаз» по скриншоту.
- **Прогресс — сразу на диск** (jsonl/atomic), а не в конце прогона: длинные обходы
обрываются.
- **Долгие обходы** — в фоновый процесс, а не в цикл интерактивных вызовов.
## Границы: где человек, а где агент
- **Пароли и второй фактор — никогда.** Не вводим и не просим в аргументах командной
строки. Уже залогиненная сессия оператора — вот твой доступ.
- **Попап «Разрешить удалённую отладку?»** — это человеческое подтверждение: агент его
не жмёт, а просит оператора нажать «Разрешить» и повторяет попытку.
- **Деньги/платежи/отправка форм с персональными данными** — только с явным
подтверждением оператора.
- **Секреты и содержимое залогиненных страниц** не пишем в логи, файлы репозитория и
вики: в mappa — только агрегаты и идентификаторы.
## Проверенные адреса и факты
- **ЧипДип, кабинет заказов:** `https://www.chipdip.ru/order/list`
(⚠️ `/cabinet` и `/orders` отдают 404 — не перебирай наугад, ссылка есть в шапке).
- Залогиненность видна в шапке кабинета (имя оператора); если видишь форму логина —
**сессия потеряна: стоп и скажи оператору**, не логинься сам.
- `about:blank`-вкладка с титулом-лошадкой в `document.title` = страницу ведёт агент.
## Так делать НЕ надо
| Соблазн | Почему нет |
|---|---|
| «Вытащу куки из Chrome и пойду `curl`'ом» | мимо канала и мимо аренды; пароль/2FA оказываются рядом; ломается при смене защиты |
| «Подниму свой Chrome с отладкой» | там **нет** его логинов → выкинет на логин/капчу, плюс это второй водитель |
| «Введу логин/пароль через `read -s`» | пароли и 2FA не вводим никогда |
| «Проверю ещё пяток URL кабинета» | адрес подтверждай по ссылке в интерфейсе, а не перебором |
| «Налью 20 запросов параллельно, быстрее» | антибот + оператор останавливает такие прогоны; один водитель, одна очередь |
Основание: базовый прогон без скила (2026-09-11) ушёл именно в «куки + curl + пароль»
мимо канала; скил закрывает этот путь.
## Красные флаги (стоп и перечитай)
- Собираешься вытащить куки / поднять свой браузер / ввести пароль или код.
- Работаешь с браузером **без** аренды (или ломишься, когда «занято»).
- Полливаешь запросами без паузы или ждёшь паузу в JS.
- Пишешь содержимое залогиненных страниц/секреты в файл, лог или вики.
## Вне скоупа
- Анонимные/антидетект-прогоны, свой профиль, `mode: fresh` — скил `browser-cdp`.
- Облачные браузеры (Browser Use Cloud и прочие) — не берём.
- Свой stdio-MCP-сервер поверх общего демона — отдельная тема.

View File

@@ -0,0 +1,98 @@
---
name: code-search
author: ours
version: 0.1.0
description: >
Use when searching code for strings, symbols, or usages — "find where X is
used", «найди, где используется», "grep for X", "where is X", "search the
repo for", any code search, or when deciding HOW to search a codebase. One
hard rule: in any tree that can contain node_modules/dist/build/.nuxt,
search with `rg` (gitignore-aware) — NEVER `grep -r` (`--include` filters
file names, not directory traversal; grep walks every node_modules entry:
measured 15+ min never-finishing vs rg 0s on the same tree). Routes:
string/symbol search → rg; tracked-files-only → git grep; whole-repo
comprehension ("what does module Y do") → interns repo_read (ask-mode);
N×M contains audits → interns grep_audit. Skip for web search
(web-search), vault search (coworker-search), already-fast tools.
---
# Code Search
Search code with the fastest correct tool for the question class. The default
`grep -r` habit is the single biggest time sink in agent work on npm/JS
projects — the fix is a different binary, not more patience.
## When to use
- Any "where is X used / where does X appear / search the repo for X" request.
- Deciding HOW to search: rg vs git grep vs intern delegation.
- A search that "feels slow" — that is a wrong-tool signal, not a slow disk.
## When NOT to use
- Web search → `web-search` skill.
- Searching the .cowork vault / memory vault → `coworker-search`.
- A question ABOUT the code ("what does module Y do", "how does the build work") → `interns.repo_read` (delegation, ask-mode per `using-interns`).
- The right tool is already running and fast.
## Core rule (one sentence)
**In any tree that can contain `node_modules` / `dist` / `build` / `.nuxt` / `vendor`, search with `rg`, never `grep -r`.**
Why — measured on `stostayer.new`, `packages/web` + `apps/web4`, 2026-08-26:
| Fact | Value |
|---|---|
| Total files in the two dirs | 113,169 |
| Of which in `node_modules` + `.nuxt` + `build` | 109,248 (**96%**) |
| `grep -rn "3590" … --include=*.vue --include=*.js … -l` | **> 15 min, never finished** (RED run: fresh unprompted agent spawned 2× `/usr/bin/grep`, still running at 200s, killed) |
| `rg -l "3590" …` (same globs) | **0s**, 3 matches |
| `rg --no-ignore "3590" …` (forced full scan incl. node_modules) | 16s |
Mechanics: `grep -r --include` filters which **file names** get read — it does
NOT stop **directory traversal**. grep stats/opens every directory entry
including node_modules (100k+ files) on every search. `rg` reads `.gitignore`
(+ `.ignore`, `.rgignore`) and skips ignored trees by default — zero flags
needed. It is already installed on this machine (ripgrep 15.x).
## Routing table
| Question class | Tool | Notes |
|---|---|---|
| Find string/symbol/usages in the working tree | `rg -n "pattern" <paths>` | gitignore-aware out of the box. `-l` → filenames only. `-g '*.ext'` to filter. |
| Only tracked files (clean, deterministic) | `git grep -n "pattern"` | uses the git index; ignores untracked + ignored. Always present even on bare boxes. |
| "I really must scan generated/vendored too" | `rg --no-ignore` | 16s on the 113k-file tree — still ~50× faster than grep. Never `grep -r` even here. |
| Whole-repo comprehension ("what does module Y do", "where is X used across the architecture") | `interns.repo_read` | delegation — ask-mode, `using-interns` skill. Packs via repomix + cheap LLM. |
| N×M contains/not-contains audit (canonical strings across many files) | `interns.grep_audit` | deterministic, no LLM call. |
## Common mistakes / rationalizations
| Excuse | Reality |
|---|---|
| "grep works, just slow" | Wrong tool. rg is a drop-in replacement on the same globs: 15 min → 0s on the same tree. |
| "--include excludes node_modules" | **False.** `--include` filters file *names* that get read, not directories *walked*. grep still traverses all 100k+ node_modules entries. |
| "Windows/Defender is just slow" | The disk is not the problem — 96% of walked files are build artifacts. rg skips them via .gitignore before the filesystem ever opens them. |
| "I need to search EVERYTHING" | Use `rg --no-ignore` (16s), still not grep (15 min). Scope with `-g '!node_modules'` if noise is the issue. |
| "rg isn't installed here" | It is (ripgrep 15.2.0). On a bare box fall back to `git grep` — git is always present. |
| "It's a one-off, speed doesn't matter" | One-off searches happen 10+ times per session. Each 15-min grep burns an entire agent turn for nothing. |
## Red flags (STOP)
- A search command starting with `grep -r` in any JS/TS/node project — rewrite to `rg` before running.
- A grep that "hasn't returned" after 30s — it is walking node_modules; kill it, use rg.
- Search results containing `node_modules/` / `.nuxt/` / `dist/` paths — you scanned garbage; redo with rg (ignore-aware).
- Writing `--include` and believing directories are excluded.
## Cross-agent applicability
Tool-level rule, works in any agent that can run shell commands (pi, claude,
codex exec, hermes). `rg` or `git grep` are the always-available core; the
intern rows are optional delegation for a local `interns` MCP
(`using-interns` skill). The core rule stands alone without them.
## Out of scope
- Semantic code search / index servers (zoekt, sourcegraph, codesearch) — YAGNI; rg removes the pain without infrastructure.
- Searching non-code stores (vaults, wikis, the web).
- Teaching rg's full flag surface — `rg --help` / man.
- mappa internals: code search stays client-side (operator decision 2026-08-25 — "rg-мост по чек-аутам", outside mappa).

View File

@@ -1,193 +0,0 @@
---
name: delegate-task
author: ours
version: 0.5.1
description: >
Use when delegating a task to another agent or project via
mcp__projects-meta__tasks_create. Every cross-project delegation is a
pair: tasks_create + covering letter to the recipient's inbox (event:
created) — a task on the board does not ping a live session. Triggers:
«делегировать таску», «delegate task», «создать задачу на агента»,
«поставить задачу агенту», «tasks_create для». Does NOT apply to
self-assigned tasks on your own board («создать задачу себе», «task for
myself», «поставить себе задачу» → using-tasks), to work you do yourself,
or to workshop-internal tasks.
---
# delegate-task
Унифицированный формат постановки задач на агентов через `mcp__projects-meta__tasks_create`. Обеспечивает что каждая делегированная задача содержит: обязательные скилы (императивный invoke), pre-flight разрешения, steering-loop поля (notify/weight/allow_upgrade).
## When to use
Перед каждым вызовом `mcp__projects-meta__tasks_create` для другого проекта или агента.
**Активируется:** «делегировать таску», «delegate task», «создать задачу на агента», «поставить задачу агенту», «tasks_create для».
**Не применяется:**
- Работа которую выполняешь сам в текущей сессии.
- Self-assigned таски на своей доске («создать задачу себе», «task for myself», «поставить себе задачу») → `using-tasks`, не делегирование. Дизамбигуатор: «на агента»/«агенту»/«в проект X» = делегирование; «себе»/«myself» = своя доска.
- Workshop-internal таски (`.workshop/.tasks/` — workshop-meta, не делегирование).
- `tasks_create` с `target=agenda` (cross-project agenda — не делегирование агенту).
## Inputs
- `target_project` — qualified `<owner>/<repo>` (обязательно)
- `slug` — kebab-case latin
- Краткое описание задачи (цель + acceptance criteria)
- `weight` — `cheap-ok | needs-claude | needs-human`
- `notify` — slug проекта-комиссионера (кому писать inbox при close/park)
- `allow_upgrade` — `true/false` (опционально; разрешить ли fallback на tier выше если нет matching backend)
Номер задаче присваивает сервер (`tasks_create` из счётчика `OpeItcLoc03/agenda/task-counter`) — постановщик номер не придумывает и не резервирует. Возвращённый `#n` из preview/confirm — машинный ключ задачи: им ссылаются блокеры, письма, decision-trail.
## Steps
### 1. Pre-flight gate (6 вопросов пользователю)
Спросить **до** составления тела задачи:
0. **Критическая инфраструктура?** — задача меняет: поллер/агент-раннер, MCP серверы (projects-meta, interns), механизм claim/close/heartbeat, deploy-инфру (traefik, docker, systemd), CI/CD пайплайны, git hooks.
- Если **да** → `weight: needs-human` принудительно, без обсуждения. Объяснить пользователю почему.
- Если **нет** → идти дальше.
1. **Интерны — разрешены?** (да/нет, per задача)
2. **Автопуш — разрешён?** (да/нет, per задача)
3. **Контекстные скилы сверх дефолтов?** — предложить по содержанию задачи (например `claude-api` для работы с Anthropic SDK, `frontend-design` для UI, `using-interns` если интерны разрешены), пользователь утверждает.
4. **notify — кому докладывать о завершении/затыке?** (slug проекта; обычно `.workshop` или `OpeItcLoc03/workshop`)
5. **Session-break после этой задачи?** — нужен ли разрыв сессии после её закрытия (domain-switch, milestone, heavy infra)?
- Если **да** → проставить `session_break` в теле задачи (см. шаблон): `true` или строка-hint с названием следующего трека. `using-tasks` остановится после close и предложит завершить сессию, не клеймя следующую задачу.
- Если **нет** → поле не добавлять (дефолт — агент продолжает `claim-next`).
### 2. Составить тело задачи по шаблону
Секции строго по порядку:
```
<Цель — одно-два предложения. Acceptance criteria если есть.>
**Спека:** <path к design-решению или .brainstorm/…> — обязательно для задач
из дизайна/решения: импл читает дизайн, не угадывает
## Обязательные скилы — вызвать до начала работы
- invoke `tdd-criteria` — до написания кода
- invoke `using-tasks` — для управления статусом задачи
- invoke `project-discipline` — дисциплина коммитов/пушей
- invoke `using-wiki` после закрытия — заингесть .wiki/concepts/<slug>.md
[если кросс-проектная: - invoke `using-projects-meta` — cross-project tasks/wiki]
[контекстные скилы из шага 1.3]
**TDD:** да | нет — <причина>
**Разрешения:** интерны: да/нет | автопуш: да/нет
**weight:** cheap-ok | needs-claude | needs-human
**notify:** <commissioning-project-slug>
[**allow_upgrade:** true/false]
[**session_break:** true | "<следующий трек / hint>"] # optional — using-tasks остановится после close, не клеймит следующую задачу
```
**Когда ставить `session_break`** (опционально; по умолчанию НЕ ставить — это маркер реальной границы, не дефолт). Три случая:
1. **Смена домена / репо** — задача завершает один трек перед переходом на несвязанный.
2. **Milestone-задача** — последняя в группе sub-tasks одной фичи.
3. **Тяжёлая инфра-задача** — shared checkout, migrations, deploy — где разумно остановиться и проверить состояние.
Значение: `true` (следующий трек = «см. STATUS.md») либо строка-hint с названием следующего трека. Потребитель — `using-tasks` v1.2.0+ (Task completion step 6): после close печатает `🔚 SESSION BOUNDARY …` и останавливается, не клеймя следующую задачу. Дизайн: `.wiki/concepts/delegate-task-session-break.md`.
**Этапные цепочки (staged breakdown):** если решение бьётся на этапы
(1 → 1b → 3), создавай каждый этап отдельной таской со `status: blocked` +
`blocker: <номера-предшественников> (#n1, #n2 — номера, не слаги; номер =
машинный ключ)`. Доска показывает порядок, поллер не возьмёт зависимую
работу раньше времени. Таски в один репо создавай последовательно, не
параллельно (иначе sha-lock конфликт — см. Failure modes).
**Почему `invoke` а не триггер-фраза:** AGENTS.md ненадёжен (уплывает при compression, слабые модели игнорируют). Тело задачи читается активно — императив `invoke` это прямая команда, не пассивный матчинг.
### 3. Dry-run preview
`tasks_create(confirm=false)` — показать пользователю preview до реального коммита.
### 4. Подтверждение и создание
После OK пользователя: `tasks_create(confirm=true)`.
### 5. Сопроводительное письмо — обязательно при кросс-проектной делегации
После создания **каждая кросс-проектная делегация** дублируется письмом в
инбокс получателя (канон — `inter-session-messaging` v2: канал Mappa, адрес
из адресной книги `~/projects/.wiki/concepts/projects-address-book.md`):
```
mcp__mappa__inbox_send(
project: <адрес-получателя>, # имя папки, из адресной книги
from: <своя-папка>,
subject: "[event: created] #n slug",
body: "1-2 строки — что за задача, почему, slug; «разбери и возьми»"
)
```
(Мутация тасок гейтится лизом проекта — `task_claim_next`; доставка письма —
карв-аут, лиза не требует.)
Причина: таска на борде **не пингует живую сессию** получателя. Поллер
подхватит по `Weight`/`Notify`, но живая интерактивная сессия узнаёт только
через inbox-монитор — т.е. через письмо. Правило «task + letter, не только
task» — общий случай (шаг 7 — его частность для downstream-задач).
Пропуск: self-assigned задачи на своей доске; `target=agenda` (общая доска,
конкретного получателя нет — steering-loop через `Notify`).
### 6. Парная review-таска (только для impl-задач)
Если задача имплементационная — создать парную `<slug>-review` (status=blocked, blocker=`#n` — номер impl-таски). Пропустить для: pointers-тасок, ops-тасок, research-тасок, любых non-impl.
**`weight` review-таски — наследовать от impl-таски, но не ниже `needs-claude`** (проставлять явно при `tasks_create`):
- impl `needs-human` → review `needs-human` (критично-инфраструктурное изменение нельзя ревьюить слабым tier'ом — ревью наследует строгость impl).
- impl `needs-claude` → review `needs-claude`.
- impl `cheap-ok` → review `needs-claude` (флор: review дисциплинарно-критична, см. What NOT to do — cheap-ok сюда не опускать).
Без явного `weight` поллер не маршрутизирует review-таску (reconciler её пропускает) — поэтому проставлять всегда, даже когда impl и review совпадают по tier'у.
### 7. Downstream-задача для ЖИВОЙ сессии → требовать task + inbox-письмо
Если тело задачи **поручает агенту самому создать downstream-задачу** для другого проекта, где работает **живая интерактивная сессия** (напр. прог сам ставит deploy-таску админу), — в ТЗ **явно потребуй И `tasks_create`, И inbox-письмо** тому проекту (`mcp__mappa__inbox_send(project=<target>, from=<своя>, subject="[event: created] #n slug", ...)`).
Причина: таска на борде живую сессию **НЕ пингует**. Поллер подхватит по `Weight`/`Notify`, но живая интерактивная сессия узнаёт только через inbox-монитор / Stop-хук — т.е. через письмо. ТЗ, требующее лишь `tasks_create`, оставляет downstream-таску висеть незамеченной, и кто-то доделывает пинг руками.
Правило: poller-driven таргет → `Weight`/`Notify` обязательны; live-сессия → inbox-письмо обязательно; **не уверен, поллер или живой — требуй ОБА.** Это же правило применяй, когда пингуешь пира сам: task + letter, не только task.
## Failure modes
- **Пользователь отказывает на pre-flight** → abort, задачу не создавать.
- **Пользователь отклоняет dry-run preview** → abort.
- **notify не указан** → переспросить, не пропускать молча. Без notify steering-loop не замыкается.
- **weight не указан** → переспросить. Без weight поллер не знает кому отдать задачу.
- **tasks_create упал** → различить: **PushRejected** (sha-lock конфликт —
репо уехало между preview и confirm; бывает при параллельном создании в один
репо) → **retry**: повторить confirm — сервер перечитает актуальный base_sha.
Другие ошибки → сообщить пользователю, не делать retry без явного запроса.
## Side effects
- Создаёт таску в target-проекте через `mcp__projects-meta__tasks_create` (Gitea commit).
- Опционально создаёт парную review-таску (status=blocked).
## What NOT to do
- Не пропускать pre-flight gate — даже если кажется что всё очевидно.
- Не использовать пассивные триггер-фразы вместо `invoke` — «tdd-criteria» в тексте слабее чем «invoke `tdd-criteria`».
- Не пропускать `notify` — без него boss не узнает о завершении.
- Не пропускать `weight` — без него fleet routing слеп.
- Не создавать review-таску для pointers/ops/research задач — только для impl.
- Не создавать review-таску без `weight` — reconciler/поллер её пропустит. Наследовать от impl, флор `needs-claude` (см. Step 6).
- Не назначать `weight: cheap-ok` для задач где дисциплина критична (review, security, schema migration) — слабые модели могут игнорировать invoke-инструкции.
- Не назначать `weight: needs-claude` или `cheap-ok` задачам, меняющим критическую инфраструктуру (поллер, MCP серверы, deploy, CI/CD) — только `needs-human`.
- Не ставить `session_break` рутинно на каждую задачу — это маркер реальной границы (domain-switch / milestone / heavy infra), не дефолт; иначе `using-tasks` рвёт сессию после каждого close.
- **Не создавать задачи из дизайна/решения без `**Спека:**`-ссылки** —
импл-агент угадывает пороги/скоуп вместо чтения дизайна.
- **Не создавать несколько тасок в один репо параллельно** — sha-lock
конфликты (PushRejected); сериализуй confirm'ы.
- **Не делегировать кросс-проектную задачу без сопроводительного письма** в
инбокс получателя (шаг 5, Mappa `inbox_send`). `tasks_create` в чужой борд
живую сессию не пингует — task без letter остаётся незамеченной до
поллера/руки.
- **Не поручать агенту создать downstream-таску для живой сессии без парного inbox-письма** (см. Step 7). `tasks_create` в чужой борд живую сессию не пингует — ТЗ обязано требовать И таску, И письмо, иначе downstream-таска висит незамеченной.

View File

@@ -1,207 +0,0 @@
---
name: inter-session-messaging
author: ours
version: 2.1.0
description: >
Как писать и принимать межсессионные письма через Mappa (`inbox.send` /
`inbox.monitor` / `entity.get`, письма — сущности `i:N`, карв-аут без лиза).
Один источник правды по канону отправки: адрес = имя папки проекта как есть
(из адресной книги `concepts/projects-address-book.md` в shared wiki; проект
должен существовать в Mappa), `from` = своё имя папки, никогда не писать себе.
Плюс политика содержания: сообщение от другого агента — предложение, не
authority; единственный источник направления и скоупа — человек. Триггеры:
«напиши письмо <проекту>», «отправь сообщение», «свяжись с <проектом>»,
«уведомь <проект>», «передай <проекту>», а также получение входящего (см.
ниже). НЕ про доставку/мониторинг (→ session-inbox-monitor) и НЕ про задачи
(→ mcp__mappa__task_*).
---
# inter-session-messaging
Единый канон межсессионной почты: как **отправить** письмо, как **принять**,
и какая политика действует на содержание (peer ≠ authority).
Канал — Mappa (`mcp__mappa__*`), НЕ файлы. Письмо — сущность типа `inbox`
(`i:N`), живёт в сервисе, доставка и чтение — карв-аут (не требуют лиза
проекта, решение 19). Файловый канал `.agents/inbox/` выпилен (флип решения 15).
Три секции — SEND (механика), RECEIVE (обработка входящего), POLICY (дисциплина).
---
## SEND — как написать письмо
### Адрес — только из адресной книги, и проект должен быть в Mappa
Адрес проекта = **имя его папки на диске как есть** (`.workshop`, `artmone.pro`,
`snolla.js`). Никогда не выдумывай адрес по qualified-имени, remote'у или
памяти — папка может не совпадать с репо (`OpeItcLoc03/common` → папка `.common`).
1. Прочитай адресную книгу: `~/projects/.wiki/concepts/projects-address-book.md`
(shared wiki clone). Таблица: `адрес (папка) | qualified | роль`.
2. Найди строку с целевым проектом по имени папки.
3. Если проекта в книге **нет** — письмо не пиши. Остановись и спроси человека
(или заведи запись в книге, если человек подтвердил адрес). Письмо по
выдуманному адресу создаёт проект-сироту в Mappa (`ensureProject`) и теряется.
4. **Проект должен существовать в Mappa**: сверь адрес со списком проектов
(`mcp__mappa__admin_status` → `projects[]` или `entity_search` type=project).
Несуществующего адреса нет в списке — остановись и спроси (или заведи проект).
### Вызов отправки
```
mcp__mappa__inbox_send(
project: <адрес получателя>, # имя папки проекта (из адресной книги)
from: <адрес отправителя>, # СВОЁ имя папки (только имя, без owner/темы)
subject: <тема>, # опционально — короткая тема
body: <markdown-тело> # свободный markdown
)
```
- `from` — **только имя своей папки**. Без owner, без описания. НЕ
`reviewer-command-index-done-ack` (тема письма — не адрес). На письмо с
выдуманным `from` нельзя ответить.
- Ответ на письмо: `inbox_send(project=<from полученного>, from=<своя папка>)`.
В `subject` — префикс `Re: `, в теле первая строка — ссылка на исходное
письмо (`i:<номер>` или его subject). Поля `in_reply_to`/`event` в Mappa нет —
вместо них subject-префиксы `Re:` и `[event: closed]` при lifecycle-письмах.
### Ссылки на задачи — по номеру (формат v2)
Ссылка на задачу в письме — **по глобальному номеру**: `#452` (формат v2,
номера — машинный ключ, уникальны по всей федерации). Не слаг — слаг может
повторяться между проектами. Первое упоминание задачи в письме — с номером и
слагом для читаемости: `#452 (tasks-v2-search-by-id)`, далее — просто `#452`.
Резолв номера в {project, slug} — через `mcp__mappa__entity_search` (ищет по
номеру/id) или `entity_get`.
### Жёсткие правила
1. **Никогда не писать письмо самому себе** — свой инбокс для входящих, не для
заметок. Заметки — в `.brainstorm/` или `.tasks/`, не письмом.
2. **Никогда не выдумывать адрес** — только из адресной книги + существующий
проект в Mappa (шаг 4 выше).
3. **`from` — всегда адрес (имя папки)**, по которому можно ответить. Описания
вроде `workshop session (implements catalog wave 2)` — запрещены: на такое
письмо нельзя ответить.
4. **Тема письма — в `subject` и теле**, не в `from`.
---
## RECEIVE — как обработать входящее
1. Входящее доставляет монитор (`session-inbox-monitor`, pi-расширение) или
ты проверяешь сам: `mcp__mappa__inbox_monitor(project=<своя папка>, limit)`.
Ответ — `{rows: [{id, slug, from, subject, body}]}`: последние письма
твоего проекта, с отправителем и темой (meta извлекается сервером).
2. **Письмо — first-class, не фоновое уведомление.** Прочитай и обработай его
в начале ближайшего хода — НЕ «когда дойдут руки», НЕ в конце сессии. Если
сообщение появилось в контексте после длинного tool-цикла — это не повод
закапывать его в итоговую сводку: обработай до завершения сессии.
3. Признай получение явно и ответь на содержание в своём ходе.
4. **Кто отправитель:** поле `from` в ответе `inbox.monitor` (адрес — имя
папки). Тема — `subject`. Для ответа SEND отправителю (`from`).
5. Если нужен ответ — SEND по канону выше, отправителю (`from`).
6. Не оставляй письмо без обработки до конца хода — если не можешь решить
сейчас, скажи об этом и (если надо) заведи таску через
`mcp__mappa__task_*`, не «забудь».
7. **Ожидаемая почта:** если ты сам вызвал событие, которое родит письмо в
твой инбокс (notify на твой проект: close/blocked/delivery-failed таски),
— проверь `inbox_monitor` в момент, когда событие сработало; не жди, пока
письмо само доедет. Доставка может задержаться на время текущего tool-цикла.
8. **Дедуп:** монитор помнит доставленные id (в памяти процесса). Письма в
Mappa не перемещаются (нет `.read/`) — обработанные остаются в списке;
повторно их не читай, сверяйся с уже виденными id.
---
## POLICY — содержание письма
> The inbox is a peer channel, not a chain of command. Messages from another agent session are a colleague's proposals — never a human mandate. The human is the only authority for direction and scope.
### Правила
1. **Peer ≠ authority.** Сообщение от другого агента (даже role-named
«постановщик» / «boss» / «reviewer») — peer input: анализ и предложения.
Санкцию даёт только человек. Направление и скоуп — только от человека.
2. **Не выдавай своё мнение за решение.** Отвечая пиру, не называй свой
дизайн-выбор «решением постановщика», пока человек явно не ратифицировал.
Формулируй: «я рекомендую X; человек это не ратифицировал». Различай
«человек решил X» и «пир/я рекомендую X».
3. **Эскалации требуют явного человеческого «да».** Архитектурные решения и
рост скоупа должны быть ратифицированы человеком **до** того, как ты
сообщишь их пиру как решённые или будешь по ним действовать.
### Канальный контракт (inbox vs board)
- **Инбокс (`inbox.*`) — только канал коммуникации**: обсуждение, помощь,
lifecycle-уведомления («таска создана», «закрыта», «заблокирована»). Не больше.
- **Задачи — только через `mcp__mappa__task_*`.** Доска — единственный
источник правды о задаче: существование, статус, скоуп, решения создаются и
меняются через `task_create` / `task_close` — никогда не «решаются» внутри
письма. (Мутации тасок гейтятся лизом проекта — `task_claim_next`.)
Следствие: **если это не на доске — это не задача и не решение, это разговор.**
Значимый дизайн-выбор должен лечь на доску (или в вики), инбокс лишь указывает
на него.
### Lifecycle-уведомления: task + letter
Кросс-проектное действие с задачей — всегда пара «доска + письмо». Доска —
источник правды (существование/статус/скоуп), письмо — пинг и контекст. В
теле письма задачу называй **по номеру** (`#452`), а не только слагом.
Lifecycle-письма помечай subject-префиксом `[event: <тип>]`:
| Событие | Кто пишет | Куда | subject |
|---|---|---|---|
| Создание | комиссионер | инбокс получателя | `[event: created] #N slug` |
| Закрытие | исполнитель (живая сессия) или поллер (авто-ран) | инбокс комиссионера (`Notify`) | `[event: closed] #N slug` |
| Блокировка/парк | то же | то же | `[event: blocked] #N slug` |
Тело письма — 1-2 строки + номера/слаги, не дублировать доску. Живая сессия
узнаёт о задаче ТОЛЬКО через письмо (борд не пингует); комиссионер узнаёт о
закрытии только через `Notify`/письмо. Правило постановки — `delegate-task`
шаг 5; правило закрытия — `using-tasks` Task completion шаг 4.
### Против чего это
Две сессии пинг-понгуют, каждая соглашается с фреймом другой и добавляет скоуп,
человек номинально в цикле. Сигнатура эхо-камеры: быстрые ответы, согласие с
твоим фреймом, рост скоупа каждый раунд. Это
`user_context_agents_path_of_least_resistance` уровнем выше: сессии обходят
человеческую ратификацию — фейковое «решено» через взаимное согласие.
### Circuit-breaker
Заметив рост скоупа без явного человеческого «да» — **остановись и спроси
человека**: «Я пир-сессия, не человек-авторитет; я эскалирую скоуп здесь; ты
реально хочешь, чтобы это ушло как решённое?»
**Multi-session caveat — не кричи «override» с частичного зрения.** Когда человек
ведёт несколько сессий, твой обзор того, что он ратифицировал, частичен. Пир,
действующий по «нератифицированному», может иметь реальную человеческую санкцию
из канала, который ты не видишь. При кажущемся нарушении — **спроси «ты
ратифицировал это в другом канале?»**, а не обвиняй. Урок 2026-06-16: workshop
назвал close в common «фейковой атрибуцией ратификации»; на деле человек
одобрил напрямую в common-канале, пока workshop ещё обсуждал. Всплыви пробел
вопросом — человек сверит каналы.
### Почему это существует
Возникло 2026-06-16: workshop и common вели многораундовый дизайн-обмен по
инбоксу; workshop эскалировал дизайн (tamper-guard → prevention → oracle-integrity
→ runner-owns-verifier → close-moves) и докладывал каждый шаг как «решение
постановщика» — подразумевая человеческую санкцию, которой не было. common
распознал эхо-камеру, прочитал свой stop-hook и корректно отказался
имплементировать нератифицированный редизайн, спросив человека. Методология
живёт в скиле, не в per-session памяти.
---
## Reference
- Доставка/мониторинг входящих: `session-inbox-monitor`.
- Адресная книга: `~/projects/.wiki/concepts/projects-address-book.md` (shared wiki).
- Список проектов Mappa: `mcp__mappa__admin_status` (карв-аут, без лиза).
- Handoff через сущность `handoff`: `session-handoff`.
- Related: `recommend-dont-menu` (стиль ответа), `project-discipline`.

View File

@@ -0,0 +1,90 @@
---
name: ops-browser
author: ours
version: 0.1.0
description: >
Use when a task needs a real browser — личный кабинет, заказы, чеки, yt-digest,
скриншот живого сайта, «дёрни внутренний API». Свой СКРЫТЫЙ браузер агента:
отдельный профиль, CDP, `fetch()` ИЗ страницы, хендофф человеку для пароля/капчи.
---
# ops-browser — свой скрытый браузер агента
**Есть задача, которой нужен браузер? Работай в своём браузере, скрыто, и не подсовывай куки.**
Профиль владеет сессией сам (куки продлеваются браузером, а не руками) — это и есть лечение
боли «куки протухли».
## Когда ЭТОТ инструмент, а когда другой
| Ситуация | Чем работать |
|---|---|
| Публичная страница без логина | `web_search` / `web_extract` / curl — браузер не нужен |
| Личный кабинет, заказы, чеки, внутренний API сайта, антибот | **`ops-browser.sh`** (этот скил) |
| Нужны ЕГО логины и ЕГО Chrome (Avito, кабинеты поставщиков) | канал оператора: Hermes `browser_exec` / pi тул `browser` / CC `chrome-devtools` — всё под арендой `driver.lock` |
| Посмотреть глазами, кликнуть по живому сайту, показать ему | панель предпросмотра (`desktop_preview` + `drive_preview`) — без JS, только текст/клики |
`ops-browser` не заменяет канал оператора: там его сессии, здесь — **мой** профиль.
И то и другое живёт под правилом «один водитель» (у ops свой замок `ops.lock`).
## Команды
```bash
OB="$HOME/.config/browser-harness/bin/ops-browser.sh"
bash "$OB" start # headless + аренда (окон нет)
bash "$OB" open https://site/path # перейти
bash "$OB" read 2000 # видимый текст страницы
bash "$OB" eval 'fetch("/api/x",{credentials:"include"}).then(r=>r.json()).then(j=>JSON.stringify(j))'
bash "$OB" screenshot [path] # PNG, печатает путь
bash "$OB" cookies https://site # имена кук (без значений)
bash "$OB" status # аренда + CDP + текущая страница
bash "$OB" stop # ШТАТНО закрыть и отпустить
bash "$OB" handoff <url> # человеку: пароль/2FA/капча (см. ниже)
```
`eval` выполняет JS **в контексте страницы** — значит `fetch()` идёт с её куками и заголовками:
так дёргают внутренние эндпоинты приложения (то, что недоступно извне и чего не умеет панель).
## Хендофф человеку (пароль, 2FA, капча, согласие)
Останавливаюсь и отдаю экран **сам**, без «скажи готово»:
1. `bash "$OB" handoff <url>` — закрывает headless (профиль нельзя открыть дважды) и поднимает
**видимое** окно ТОГО ЖЕ профиля на нужной странице;
2. человек вводит, что нужно (пароль/2FA/капчу вводит только он);
3. признак успеха ловлю сам: URL ушёл со страницы логина/auth **или** выросли куки домена;
4. штатно закрываю окно и возвращаюсь в headless — логин остался в профиле.
Скриншот делаю **до** шага (что от человека хотят) и **после** (что получилось); **во время ввода
пароля не снимаю**. Если признак успеха не увидел — окно остаётся открытым, а я говорю об этом прямо.
## Границы (не двигаются)
- Пароли, 2FA, капчу — **вводит человек**. Я к ним не подхожу.
- Деньги, оформление заказов, формы с перс.данными — только с явного согласия оператора.
- Куки не выгружаю и не расшифровываю; содержимое залогиненных страниц не уходит в логи/вику.
- Антибот-челленджи не обхожу; если сайт невзлюбил `headless` — это повод для `handoff`, а не для трюков.
## Грабли (стоили времени, проверены живьём)
- **Закрывать только штатно** (`stop` → `Browser.close`). Жёсткий kill может не сбросить профиль →
потеря логина. Сессионные куки (без срока) перезапуск не переживают по дизайну — настоящие логины живут.
- **MSYS-пути**: нативным программам нужен вид `C:/...` (`cygpath -m`), а `powershell -File` —
только `C:\...` (`cygpath -w`). Иначе «модуль не найден» / «файл .ps1 не найден».
- **Экранирование PowerShell внутри bash-строки тихо ломается** (`$_` подменяется) — PS-запросы
держим в отдельных `.ps1`.
- **Профиль нельзя открыть дважды** — перед видимым окном headless обязан остановиться (это делает `handoff`).
- **Профиль**: `~/.config/browser-harness/profiles/ops`; порт CDP: `OPS_CDP_PORT` (9346).
## Аренда
```bash
BL="$HOME/.config/browser-harness/bin/browser-lease.sh"
bash "$BL" --lock ops status # состояние ops-замка (у Chrome оператора — driver.lock)
```
Чужой держатель `ops.lock` → `start` честно отказывает (rc=1). Мёртвый держатель отпускается по PID/TTL.
Идёшь в браузер **сам** (в обход `ops-browser.sh`)? Возьми `ops.lock` так же, как любой другой харнесс.
Контракт: mappa `concepts/ops-browser-contract` (проект `pi-extensions`),
требования `requirements:42`, план `plan:35`. Исходники: репо `pi-extensions/scripts/browser/`
(установка `just install-browser`).

View File

@@ -39,7 +39,7 @@ Karpathy / `.tasks/` (см. using-wiki/using-tasks, legacy-раздел).
| `README.md` | minimal stub | Skipped if file exists. | | `README.md` | minimal stub | Skipped if file exists. |
| вики | mappa (`using-wiki`) | сущности `type=wiki` в сервисе; файловый layout — только вне mappa (легаси). | | вики | mappa (`using-wiki`) | сущности `type=wiki` в сервисе; файловый layout — только вне mappa (легаси). |
| таски | mappa (`using-tasks`) | сущности `type=task` в сервисе; файловый `.tasks/` — только вне mappa (легаси). | | таски | mappa (`using-tasks`) | сущности `type=task` в сервисе; файловый `.tasks/` — только вне mappa (легаси). |
| `AGENTS.md` | `assets/AGENTS.md.template` | **Canon** — skill triggers (`use project wiki`, `use task management system`, etc.). On non-Windows hosts, swap the `we're on Windows` line for `we're on Linux` / `we're on macOS`. On upgrade, the template is treated as a canonical set and merged idempotently — only missing trigger lines are appended after user confirm. Re-runs are no-ops. | | `AGENTS.md` | `assets/AGENTS.md.template` | **Canon** — mappa-agnostic generic triggers (caveman, pull remote before work, tdd, interns, recommend, platform). Mappa-специфичные триггеры (`inbox monitor: raise on start`, `session sync: write to mappa`, `use project wiki`, `use task management system`, `check across all projects`) инжектятся через mappa-bootstrap (Step 5.7.2). On non-Windows hosts, swap the `we're on Windows` line for `we're on Linux` / `we're on macOS`. On upgrade, the template is treated as a canonical set and merged idempotently — only missing generic trigger lines are appended after user confirm. Re-runs are no-ops. |
| `CLAUDE.md` | generated pointer | `Canon is AGENTS.md. Read AGENTS.md.` — legacy pointer for tooling that looks for the old name. | | `CLAUDE.md` | generated pointer | `Canon is AGENTS.md. Read AGENTS.md.` — legacy pointer for tooling that looks for the old name. |
| `.wiki/concepts/bootstrap-manifest.md` | generated | Records which skill versions initialized the project, so cross-project layout drift is debuggable. | | `.wiki/concepts/bootstrap-manifest.md` | generated | Records which skill versions initialized the project, so cross-project layout drift is debuggable. |
@@ -53,7 +53,7 @@ Karpathy / `.tasks/` (см. using-wiki/using-tasks, legacy-раздел).
3. **Steps 1–5.** Create or skip each piece in order — git, README, вики/таски 3. **Steps 1–5.** Create or skip each piece in order — git, README, вики/таски
(mappa, см. using-wiki/using-tasks), `AGENTS.md` + `CLAUDE.md` pointer. (mappa, см. using-wiki/using-tasks), `AGENTS.md` + `CLAUDE.md` pointer.
4. **Step 5.5.** Write `bootstrap-manifest.md` recording the versions of 4. **Step 5.5.** Write `bootstrap-manifest.md` recording the versions of
`project-bootstrap`, `project-discipline`, `setup-interns`, and `project-bootstrap`, `setup-interns`, and
`using-interns` used. `using-interns` used.
5. **Step 5.6.** Skill dependencies check. Walk the canonical trigger list 5. **Step 5.6.** Skill dependencies check. Walk the canonical trigger list
in `AGENTS.md`, look each up in an embedded `trigger → fulfiller` map, in `AGENTS.md`, look each up in an embedded `trigger → fulfiller` map,
@@ -102,8 +102,9 @@ target with `CLAUDE_SKILLS_DIR=/path bash scripts/install.sh …`.
- [`using-wiki`](../using-wiki/) — runtime policy for the mappa wiki (v2). - [`using-wiki`](../using-wiki/) — runtime policy for the mappa wiki (v2).
- [`using-tasks`](../using-tasks/) — runtime policy for the mappa task board (v2). - [`using-tasks`](../using-tasks/) — runtime policy for the mappa task board (v2).
- [`project-discipline`](../project-discipline/) — cross-project rules - kzntsv-flavored cross-project discipline (activated per-project by
activated by the `follow project discipline` trigger. `mappa-bootstrap`, which selects the methodology flavor) — moved to
`victor/mappa-vitya-skills` (легаси, поглощено монорепо) — mappa-kzntsv-project-discipline.
- [`setup-interns`](../setup-interns/), [`using-interns`](../using-interns/) — - [`setup-interns`](../setup-interns/), [`using-interns`](../using-interns/) —
pair behind the `delegate to interns when allowed` trigger; cheap-LLM pair behind the `delegate to interns when allowed` trigger; cheap-LLM
delegation under a per-session permission grant. delegation under a per-session permission grant.

View File

@@ -1,12 +1,15 @@
--- ---
name: project-bootstrap name: project-bootstrap
author: ours author: ours
version: 2.1.0 version: 3.3.0
description: > description: >
Initializes or upgrades a project in the current folder: git, .gitignore, README.md, Initializes or upgrades a project in the current folder: git, .gitignore, README.md,
.wiki/ using Karpathy's method, .tasks/ for task tracking, AGENTS.md (canon) with .wiki/ using Karpathy's method, .tasks/ for task tracking, AGENTS.md (canon) with
skill triggers + CLAUDE.md legacy pointer. skill triggers + CLAUDE.md legacy pointer.
Creates remote Gitea repo and syncs projects-meta cache for greenfield projects. Creates remote Gitea repo and syncs projects-meta cache for greenfield projects.
Includes the mappa-bootstrap-project module (v3, решение 4 mappa-as-product):
mappa MCP connect + mappa-конвенции + методика-install (версия в манифест).
Creates the `.mappa` marker (wiki:3340) so the folder is a mappa project.
Use this skill when the user says "initialize project", "bootstrap", "setup project", Use this skill when the user says "initialize project", "bootstrap", "setup project",
"upgrade project", "add wiki", "add tasks", "start project", "set everything up", "upgrade project", "add wiki", "add tasks", "start project", "set everything up",
"create new project", or launches the agent in a new folder and wants a full setup. "create new project", or launches the agent in a new folder and wants a full setup.
@@ -34,6 +37,7 @@ ls -A 2>/dev/null | grep -q . && echo "empty:no" || echo "empty:yes"
[ -d .tasks ] && echo "tasks:yes" || echo "tasks:no" [ -d .tasks ] && echo "tasks:yes" || echo "tasks:no"
[ -f CLAUDE.md ] && echo "claude:yes" || echo "claude:no" [ -f CLAUDE.md ] && echo "claude:yes" || echo "claude:no"
[ -f README.md ] && echo "readme:yes" || echo "readme:no" [ -f README.md ] && echo "readme:yes" || echo "readme:no"
[ -d .mappa ] && echo "mappa-marker:yes" || echo "mappa-marker:no"
``` ```
Determine mode: Determine mode:
@@ -112,7 +116,7 @@ source ~/.config/projects-mcp/auth.toml 2>/dev/null || true
Get-Content ~/.config/projects-mcp/auth.toml | Select-String "base_url|token" Get-Content ~/.config/projects-mcp/auth.toml | Select-String "base_url|token"
``` ```
If auth file missing → stop and tell user: run `/setup-projects-meta` first. If auth file missing → stop and tell the user (нужны Gitea-креды; скил `setup-projects-meta` удалён 2026-08-25).
### Validate project name ### Validate project name
@@ -198,7 +202,7 @@ v2 (mappa wiki-тулы). Файловый `.wiki/` — только для пр
entities/ ← entity pages (people, services, modules) — empty .gitkeep entities/ ← entity pages (people, services, modules) — empty .gitkeep
concepts/ ← concept / design decision pages — empty .gitkeep concepts/ ← concept / design decision pages — empty .gitkeep
packages/ ← package pages — empty .gitkeep packages/ ← package pages — empty .gitkeep
sources/ ← one summary per ingested source — empty .gitkeep summaries/ ← one summary per ingested source (LLM, raw_path) — empty .gitkeep
``` ```
Page-level workflow (ingest, query, lint) and file formats are owned by the Page-level workflow (ingest, query, lint) and file formats are owned by the
@@ -223,7 +227,7 @@ file overrides the skill where they conflict.
- `entities/` — discrete things the project tracks (people, services, modules). - `entities/` — discrete things the project tracks (people, services, modules).
- `concepts/` — recurring ideas, design decisions, gotchas. - `concepts/` — recurring ideas, design decisions, gotchas.
- `packages/` — code packages this project produces or consumes. - `packages/` — code packages this project produces or consumes.
- `sources/` — one summary page per ingested external doc; frontmatter carries `ingested:` and `raw_path:`. - `summaries/` — one summary page per ingested external doc; frontmatter carries `ingested:` and `raw_path:`.
- `overview.md` — single project-wide overview. - `overview.md` — single project-wide overview.
## Naming ## Naming
@@ -298,7 +302,7 @@ Parseable: `grep "^## \[" .wiki/log.md | tail -20`.
**Immutable.** Read, never edit. The only allowed modification is appending a `> Status:` blockquote when the user explicitly asks for a status audit. **Immutable.** Read, never edit. The only allowed modification is appending a `> Status:` blockquote when the user explicitly asks for a status audit.
Place raw inputs here — articles, transcripts, PDFs, screenshots — exactly as they came in. The agent reads from `raw/`, writes summaries into `../sources/`, and never modifies raw files. Place raw inputs here — articles, transcripts, PDFs, screenshots — exactly as they came in. The agent reads from `raw/`, writes summaries into `../summaries/`, and never modifies raw files.
For large or path-sensitive sources that live outside the repo, register them here: For large or path-sensitive sources that live outside the repo, register them here:
@@ -307,7 +311,7 @@ For large or path-sensitive sources that live outside the repo, register them he
\`\`\` \`\`\`
``` ```
The empty subdirectories (`entities/`, `concepts/`, `packages/`, `sources/`) The empty subdirectories (`entities/`, `concepts/`, `packages/`, `summaries/`)
each get a `.gitkeep` so git tracks them. each get a `.gitkeep` so git tracks them.
--- ---
@@ -385,22 +389,24 @@ Template contents (`assets/AGENTS.md.template` — source of truth):
# Agent instructions. Each line is a trigger for an installed skill. # Agent instructions. Each line is a trigger for an installed skill.
talk like a caveman talk like a caveman
use project wiki
use task management system
check across all projects
pull remote before work pull remote before work
follow project discipline
follow tdd-criteria follow tdd-criteria
delegate to interns when allowed delegate to interns when allowed
recommend, don't menu recommend, don't menu
we're on Windows we're on Windows
``` ```
The `check across all projects` line activates the `using-projects-meta` skill Mappa-специфичные триггеры (`check across all projects`, `inbox monitor:
so cross-project task aggregation and the shared `projects-wiki` are available raise on start`, `use project wiki`, `use task management system`, `session
without an explicit verbal trigger. The skill is a no-op until the sync: write to mappa`) **не в шаблоне** — инжектятся через mappa-bootstrap
`projects-meta-mcp` server is registered — install via `setup-projects-meta` (Step 5.7.2), project-bootstrap mappa-agnostic. `check across all projects`
on a fresh machine if `mcp__projects-meta__*` tools are missing. активирует **mappa** tooling (`mcp__mappa__*`) — cross-project boards, shared
wiki и реестр проектов живут в mappa.
The file-based `projects-meta-mcp` and its skills (`using-projects-meta`,
`setup-projects-meta`, `meta-host-routing`, `setup-wiki`,
`setup-tasks`) were removed 2026-08-25; the shared `projects-wiki` files are
stubs «не читать, не править» — канон mappa shared-scope.
The `pull remote before work` line activates the `pulling-before-work` skill, The `pull remote before work` line activates the `pulling-before-work` skill,
which runs one `git pull --ff-only` at session start (and on explicit re-sync which runs one `git pull --ff-only` at session start (and on explicit re-sync
@@ -410,15 +416,6 @@ upstream — never auto-merges, stashes, or pushes. Install the skill on the hos
if `pulling-before-work` is not in `~/.claude/skills/`; otherwise the trigger is if `pulling-before-work` is not in `~/.claude/skills/`; otherwise the trigger is
silently dead like any other absent skill. silently dead like any other absent skill.
The `follow project discipline` line activates the `project-discipline` skill,
which codifies four cross-project rules: (1) project AGENTS.md / CLAUDE.md /
.wiki/CLAUDE.md / .tasks/ override defaults from any other skill; (2) all work on master/main,
no feature branches without explicit user approval; (3) version bump on every
edit of versioned artifacts per semver, recorded in commit; (4) commit freely,
push only after explicit per-session approval. Install the skill on the host
if `project-discipline` is not in `~/.claude/skills/`; otherwise the trigger is
silently dead like any other absent skill.
The `follow tdd-criteria` line activates the `tdd-criteria` skill, which enforces The `follow tdd-criteria` line activates the `tdd-criteria` skill, which enforces
test-driven development by default with four bright-line carve-outs (visual CSS, test-driven development by default with four bright-line carve-outs (visual CSS,
spike exploration, oneshot scripts, pure wrappers) and four anti-loophole rules spike exploration, oneshot scripts, pure wrappers) and four anti-loophole rules
@@ -432,8 +429,8 @@ which lets Claude offload predictable bulk I/O and summarization tasks
(reading 3+ files, distilling long transcripts) to cheap intern LLMs via the (reading 3+ files, distilling long transcripts) to cheap intern LLMs via the
local `interns` MCP server (`mcp__interns__bulk_text_read`, local `interns` MCP server (`mcp__interns__bulk_text_read`,
`mcp__interns__transcript_distill`, etc.) — saves Anthropic quota at ~125× the `mcp__interns__transcript_distill`, etc.) — saves Anthropic quota at ~125× the
per-call cost reduction on bulk reads. Per-session permission grant mirrors per-call cost reduction on bulk reads. Per-session permission grant mirrors the
`project-discipline` Rule 4: ask-mode default, conversational grant / revoke, `mappa-kzntsv-project-discipline` Rule 4 (skill moved from `victor/mappa-vitya-skills`, легаси, поглощено монорепо): ask-mode default, conversational grant / revoke,
always-ask paths for `.env` / secrets / keys / SSH credentials even with an always-ask paths for `.env` / secrets / keys / SSH credentials even with an
active grant, session-end reset. The skill is a no-op until the `interns` MCP active grant, session-end reset. The skill is a no-op until the `interns` MCP
server is registered — install via `setup-interns` on a fresh machine if server is registered — install via `setup-interns` on a fresh machine if
@@ -476,9 +473,14 @@ Skills used to initialize this project's `.wiki/` and `.tasks/` layout, with the
| Skill | Version | Role | | Skill | Version | Role |
|---|---|---| |---|---|---|
| `project-bootstrap` | <version> | orchestrator | | `project-bootstrap` | <version> | orchestrator |
| `project-discipline` | <version> | cross-project policy |
| `setup-interns` | <version> | interns MCP server install (one-time, per machine) | | `setup-interns` | <version> | interns MCP server install (one-time, per machine) |
| `using-interns` | <version> | interns runtime policy + per-session permission grant | | `using-interns` | <version> | interns runtime policy + per-session permission grant |
| `mappa-*` (методика, модуль 5.7) | <version of reference-package skills> | mappa-циклы: session-orient / task-work / knowledge / messaging / delegation / brainstorm-promote / closing-ritual |
Модуль `mappa-bootstrap-project` (решение 4 mappa-as-product) фиксирует
версию методики в этой строке — читать `version:` из frontmatter каждого
mappa-скилла, не хардкодить. Если пакет не установлен — `unknown` (видно
в депс-чеке 5.6).
This file is overwritten if `project-bootstrap` is re-run on the same project. For history, use `git log .wiki/concepts/bootstrap-manifest.md`. This file is overwritten if `project-bootstrap` is re-run on the same project. For history, use `git log .wiki/concepts/bootstrap-manifest.md`.
``` ```
@@ -507,13 +509,16 @@ Mismatch between template and map → silent gaps in the recommendation.
| `talk like a caveman` | `caveman` | skill | `~/.claude/skills/caveman/SKILL.md` | `bash scripts/install.sh caveman` | | `talk like a caveman` | `caveman` | skill | `~/.claude/skills/caveman/SKILL.md` | `bash scripts/install.sh caveman` |
| `use project wiki` | `using-wiki` | skill | `~/.claude/skills/using-wiki/SKILL.md` | `bash scripts/install.sh using-wiki` | | `use project wiki` | `using-wiki` | skill | `~/.claude/skills/using-wiki/SKILL.md` | `bash scripts/install.sh using-wiki` |
| `use task management system` | `using-tasks` | skill | `~/.claude/skills/using-tasks/SKILL.md` | `bash scripts/install.sh using-tasks` | | `use task management system` | `using-tasks` | skill | `~/.claude/skills/using-tasks/SKILL.md` | `bash scripts/install.sh using-tasks` |
| `check across all projects` | `using-projects-meta` | skill | `~/.claude/skills/using-projects-meta/SKILL.md` | `bash scripts/install.sh using-projects-meta` | | `check across all projects` | mappa (`mcp__mappa__*`) | MCP | `mcpServers.mappa` in `~/.claude.json` | — |
| `pull remote before work` | `pulling-before-work` | skill | `~/.claude/skills/pulling-before-work/SKILL.md` | `bash scripts/install.sh pulling-before-work` | | `pull remote before work` | `pulling-before-work` | skill | `~/.claude/skills/pulling-before-work/SKILL.md` | `bash scripts/install.sh pulling-before-work` |
| `session handoff: read on start, write on end` | `session-handoff` | skill | `~/.claude/skills/session-handoff/SKILL.md` | `bash scripts/install.sh session-handoff` | | `session handoff: read on start, write on end` | `session-handoff` | skill | `~/.claude/skills/session-handoff/SKILL.md` | `bash scripts/install.sh session-handoff` |
| `follow project discipline` | `project-discipline` | skill | `~/.claude/skills/project-discipline/SKILL.md` | `bash scripts/install.sh project-discipline` |
| `follow tdd-criteria` | `tdd-criteria` | skill | `~/.claude/skills/tdd-criteria/SKILL.md` | `bash scripts/install.sh tdd-criteria` | | `follow tdd-criteria` | `tdd-criteria` | skill | `~/.claude/skills/tdd-criteria/SKILL.md` | `bash scripts/install.sh tdd-criteria` |
| `delegate to interns when allowed` | `using-interns` | skill | `~/.claude/skills/using-interns/SKILL.md` | `bash scripts/install.sh using-interns` | | `delegate to interns when allowed` | `using-interns` | skill | `~/.claude/skills/using-interns/SKILL.md` | `bash scripts/install.sh using-interns` |
| `recommend, don't menu` | `recommend-dont-menu` | skill | `~/.claude/skills/recommend-dont-menu/SKILL.md` | `bash scripts/install.sh recommend-dont-menu` | | `recommend, don't menu` | `recommend-dont-menu` | skill | `~/.claude/skills/recommend-dont-menu/SKILL.md` | `bash scripts/install.sh recommend-dont-menu` |
| `use project wiki` | `mappa-knowledge` | skill | см. mappa-bootstrap (репо mappa) | `cd <mappa-repo> && bash skills/mappa-bootstrap/assets/install.sh` |
| `use task management system` | `mappa-task-work` | skill | см. mappa-bootstrap (репо mappa) | `cd <mappa-repo> && bash skills/mappa-bootstrap/assets/install.sh` |
| `inbox monitor: raise on start` | `mappa-session-orient` | skill | см. mappa-bootstrap (репо mappa) | `cd <mappa-repo> && bash skills/mappa-bootstrap/assets/install.sh` |
| `session sync: write to mappa` | `mappa-session-orient` | skill | см. mappa-bootstrap (репо mappa) | `cd <mappa-repo> && bash skills/mappa-bootstrap/assets/install.sh` |
| `we're on Windows` / `we're on Linux` / `we're on macOS` | `active-platform` | skill | `~/.claude/skills/active-platform/SKILL.md` | `bash scripts/install.sh active-platform` | | `we're on Windows` / `we're on Linux` / `we're on macOS` | `active-platform` | skill | `~/.claude/skills/active-platform/SKILL.md` | `bash scripts/install.sh active-platform` |
### Algorithm ### Algorithm
@@ -527,7 +532,11 @@ Mismatch between template and map → silent gaps in the recommendation.
match any row are user-custom — skip silently. The platform line matches match any row are user-custom — skip silently. The platform line matches
the `active-platform` row regardless of which platform is pinned. the `active-platform` row regardless of which platform is pinned.
3. For each matched canonical line, check the detection path: 3. For each matched canonical line, check the detection path:
- `kind: skill` → does `~/.claude/skills/<name>/SKILL.md` exist? - `kind: skill` → does `~/.claude/skills/<name>/SKILL.md` **or**
`~/.agents/skills/<name>/SKILL.md` exist? (Skill installs can land in
either host path — `scripts/install.sh` writes `~/.claude/skills/`, a
manual/alternate install may use `~/.agents/skills/`; a skill present in
either path fulfills the trigger. Same two-path rule as Step 5.7.3.)
- `kind: plugin` → does `~/.claude/plugins/installed_plugins.json` contain - `kind: plugin` → does `~/.claude/plugins/installed_plugins.json` contain
the plugin key under `plugins`? (Treat malformed JSON as "missing" and the plugin key under `plugins`? (Treat malformed JSON as "missing" and
continue — don't crash the bootstrap over a detection edge case.) continue — don't crash the bootstrap over a detection edge case.)
@@ -572,12 +581,160 @@ Mismatch between template and map → silent gaps in the recommendation.
`setup-X` at first use; bootstrap doesn't duplicate that detection. `setup-X` at first use; bootstrap doesn't duplicate that detection.
- The `~/.claude/skills/` and `~/.claude/plugins/` paths resolve identically - The `~/.claude/skills/` and `~/.claude/plugins/` paths resolve identically
on Windows / Linux / macOS — `~` works under git-bash too. on Windows / Linux / macOS — `~` works under git-bash too.
- **Detection paths (unified with Step 5.7.3):** a `kind: skill` fulfiller is
considered present if its `SKILL.md` exists in `~/.claude/skills/<name>/`
OR `~/.agents/skills/<name>/`. The dependency tables below list the
canonical install path (`~/.claude/skills/`, what `scripts/install.sh`
writes); detection itself accepts both.
- **Hard rule — never auto-install.** Slash commands aren't callable from a - **Hard rule — never auto-install.** Slash commands aren't callable from a
skill, and silently mutating user-level skill / plugin state without skill, and silently mutating user-level skill / plugin state without
consent is overreach. The recommendation is informational. The user can consent is overreach. The recommendation is informational. The user can
install some / all / none of the recommendations, or remove canonical install some / all / none of the recommendations, or remove canonical
lines from `AGENTS.md` to lean the project's trigger set down. lines from `AGENTS.md` to lean the project's trigger set down.
---
## Step 5.7 — mappa-bootstrap-project (модуль, решение 4 mappa-as-product)
> Спека: `.wiki/concepts/mappa-as-product.md` (wiki:2672), решение 4. Модуль
> вызывается project-bootstrap'ом как шаг в режимах greenfield-full и upgrade.
> Скоуп: connect (MCP) + mappa-конвенции в AGENTS.md (idempotent merge) +
> методика-install (пакет из репо, версия в манифест) + manifest/deps-check.
### 5.7.1 — Connect (MCP)
Проверить, что mappa MCP-сервер зарегистрирован на этой машине. Канон —
`~/.claude.json` → `mcpServers.mappa` (stdio: `node <repo>/dist/src/mcp-entry.js`,
env `MAPPA_CORE_URL` + `MAPPA_API_TOKEN`). pi-рантайм читает ту же
регистрацию через MCP-адаптер.
```bash
# POSIX / Windows (git-bash):
python -c "import json; d=json.load(open('$HOME/.claude.json')); print('mappa' in d.get('mcpServers', {}))"
```
- **Зарегистрирован** → пропустить, идти к 5.7.2.
- **Не зарегистрирован** → печать одного информационного блока (НЕ
авто-инсталл, то же правило что 5.6):
```
ℹ️ mappa MCP не зарегистрирован (~/.claude.json mcpServers.mappa отсутствует).
Установка: собери репо mappa (npm run build) и добавь в mcpServers:
{ "type": "stdio", "command": "node",
"args": ["<mappa-repo>/dist/src/mcp-entry.js"],
"env": { "MAPPA_CORE_URL": "...", "MAPPA_API_TOKEN": "..." } }
Секреты — из pass (см. secret:<path> реф-стиль, wiki:2672 решение 11).
```
mappa-конвенции в AGENTS.md (5.7.2) можно добавлять и без MCP-регистрации
— триггеры будут ждать установки сервера (как любой absent-скилл).
### 5.7.2 — mappa-конвенции в AGENTS.md (инъекция через mappa-bootstrap)
`project-bootstrap` — mappa-agnostic: mappa-триггеры **не хардкодятся** в
шаблоне (см. `assets/AGENTS.md.template`). Инъекция канонического набора
mappa-триггеров (`inbox monitor: raise on start`, `session sync: write to
mappa`, `use project wiki`, `use task management system`, `check across all
projects`) — через скил `mappa-bootstrap` (репо mappa, единый источник):
```bash
bash <mappa>/skills-core/mappa-bootstrap/assets/install.sh --triggers <project-dir>
```
После инъекции — **верифицировать** наличие строк (substring-проверка, та же
машинерия что Step 5 upgrade-merge). Если пользователь сознательно убрал
mappa-триггеры из AGENTS.md — не возвращать (уважать выбор). Источник истины
набора — mappa-bootstrap, НЕ шаблон project-bootstrap.
### 5.7.3 — методика-install (пакет из репо mappa, версия в манифест)
Методика = reference-пакет (wiki:2672 решение 3/6): mappa-скилы живут в
**репо mappa** (`mappa/skills/`, релокация task:1323, коммит 5301e85) — НЕ
в репо skills. project-bootstrap НЕ хранит тела и НЕ дублирует пути
(мёртвый маппинг на `scripts/install.sh mappa-*` убран, task:1339):
установка/триггеры/deps-check mappa-скилов делегируются скилу
`mappa-bootstrap` (репо mappa, спека wiki:3265).
1. Определить список mappa-циклов: `mappa-session-orient`,
`mappa-task-work`, `mappa-knowledge`, `mappa-messaging`,
`mappa-delegation`, `mappa-brainstorm-promote`, `mappa-closing-ritual`
(плюс остальные из `mappa/skills/`).
2. Проверить установку по правилу детекта Step 5.6 (оба пути:
`~/.claude/skills/` и `~/.agents/skills/`)? → да: пропустить
(upgrade-императив не дублировать).
3. Нет → печать информационного блока (НЕ авто-инсталл, правило 5.6):
```
ℹ️ Методика mappa не установлена. Установка (скил mappa-bootstrap,
репо mappa, НЕ skills-репо):
cd <mappa-repo> && bash skills/mappa-bootstrap/assets/install.sh
```
4. Версия методики фиксируется в bootstrap-manifest (5.7.4): читать
`SKILL.md` frontmatter каждого mappa-скилла (`version:`), не хардкодить.
### 5.7.4 — manifest/deps-check
Манифест (Step 5.5) дополняется строкой методики — версия = версия
reference-пакета (репо mappa, `version` из frontmatter скиллов; пакетная
версия — `mappa-bootstrap` из `mappa/skills/mappa-bootstrap/SKILL.md`).
Добавить в таблицу манифеста:
| Skill | Version | Role |
|---|---|---|
| `mappa-bootstrap-project` (модуль) | <project-bootstrap version> | connect + конвенции + методика-install |
| `mappa-bootstrap` (скил, репо mappa) | <mappa-bootstrap version> | установка/триггеры/deps-check mappa-скилов |
Deps-check (Step 5.6): mappa-триггеры (`inbox monitor: raise on start`,
`use project wiki`, `use task management system`) маппятся на fulfiller'ы
через скил `mappa-bootstrap` — `bash <mappa>/skills/mappa-bootstrap/assets/install.sh --check`
(источник истины — `mappa/skills/`, НЕ репо skills; мёртвые пути
`~/.claude/skills/mappa-*/SKILL.md` из таблицы убраны, task:1339).
Недостающие mappa-скиллы → в блок рекомендаций 5.6 (тем же форматом,
install-команда — скил mappa-bootstrap, см. 5.7.3).
---
## Step 5.8 — `.mappa` маркер (контракт wiki:3340)
Машиночитаемый маркер проекта в корне папки (схема v1 — `.mappa/config.yaml`):
гейт mappa-скилов («без маркера папка не участвует в mappa-операциях»,
task:1546) + признак корня проекта для харнессов. Создаётся на bootstrap —
без ручного прогона генератора (task:1583). Детерминированный рендер:
фиксированный порядок полей, без секретов, без timestamp — повторный запуск
no-op (`keep`).
1. **Собрать значения** (реестр mappa → локальное знание):
- `project` — канон папки (`basename "$PWD"`); если проект уже в реестре
(`projects_resolve`) — сверить, не расходится ли;
- `tenant` — `MAPPA_TENANT` (по умолчанию `vitya`);
- `url` — `MAPPA_CORE_URL` (без trailing slash);
- `git_provider` — из реестра `projects.git_provider` (например `gitea`),
иначе из шага 1.5 (создано через Gitea API → gitea); опционально;
- `git` — `projects.qualified` (owner/repo) из реестра, иначе из remote
шага 1.5; опционально (опустить, если неизвестно).
2. **Записать маркер** (скрипт — ассет этого скила, реализует контракт
wiki:3340; в репо: `skills/project-bootstrap/assets/dot_mappa_marker.py`):
```bash
python assets/dot_mappa_marker.py write \
--project "$(basename "$PWD")" --tenant vitya --url "$MAPPA_CORE_URL" \
--git-provider gitea --git "$OWNER/$REPO"
```
Без `--git-provider`/`--git`, если поля неизвестны. Повторный прогон —
no-op (`keep`); отличающийся существующий маркер без `--force` НЕ
перезаписывается — покажи diff и спроси (правило «never overwrite»).
3. **Верифицировать**: `python assets/dot_mappa_marker.py check` → exit 0.
4. **Контракт-тест** (TDD, task:1583): `python assets/test_dot_mappa_marker.py`
— «после bootstrap есть `.mappa/config.yaml`», детерминизм, без секретов,
порядок полей, идемпотентность.
Маркер публичен (без секретов) и попадает в коммит шага 6. Валидный
существующий маркер не трогаем.
---
## Step 6 — Commit ## Step 6 — Commit
```bash ```bash
@@ -602,11 +759,13 @@ Print a final report:
✅ Done! Created: ✅ Done! Created:
.wiki/ — project wiki (Karpathy method) .wiki/ — project wiki (Karpathy method)
.tasks/ — task tracking system .tasks/ — task tracking system
.mappa/ — mappa project marker (wiki:3340, schema v1)
AGENTS.md — skill triggers (canon) AGENTS.md — skill triggers (canon)
CLAUDE.md — legacy pointer CLAUDE.md — legacy pointer
.gitignore — standard template .gitignore — standard template
README.md — starter file README.md — starter file
remote — Gitea repo created and pushed remote — Gitea repo created and pushed
mappa — mappa-bootstrap-project: connect + конвенции + методика (модуль 5.7)
Skipped (already existed): Skipped (already existed):
git — left untouched git — left untouched
@@ -622,10 +781,10 @@ Remote: <Gitea URL>
--- ---
## Step 8 — projects-meta sync (greenfield-full mode) ## Step 8 — mappa registry (greenfield-full mode)
Only in **greenfield-full** mode. Re-sync the projects-meta cache so the new Only in **greenfield-full** mode. Register the new project in mappa
project becomes visible to `mcp__projects-meta__*` tools. (`mcp__mappa__projects_register`) so it becomes visible in the registry.
```bash ```bash
# POSIX: # POSIX:

View File

@@ -1,17 +1,25 @@
# AGENTS.md # AGENTS.md
# Agent instructions. Each line is a trigger for an installed skill. # Agent instructions. Each line is a trigger for an installed skill.
# #
# Inter-session mail channel is Mappa (mcp__mappa__inbox_send/inbox_monitor), # mappa-специфичные триггеры (inbox monitor: raise on start, session sync:
# NOT files. This line opts the project into inbox delivery at session start: # write to mappa, use project wiki, use task management system, check across
inbox monitor: raise on start # all projects) НЕ хардкодятся здесь — project-bootstrap mappa-agnostic. Они
# инжектятся при создании/апгрейде проекта через mappa-bootstrap:
# bash <mappa>/skills-core/mappa-bootstrap/assets/install.sh --triggers <dir>
# (см. Step 5.7.2 — mappa-конвенции в AGENTS.md, делегирование в mappa-bootstrap)
# Search rule
⛔ Never walk `node_modules/`, `dist/`, `build/`, `.nuxt/` (or any parent tree
containing them) with non-gitignore-aware search tools — measured 3701s vs rg
0s (2026-08-26). Use `rg` and NEVER `rg --no-ignore`/`-u` (those bypass the
ignore protection and walk node_modules again). Also no `grep -r`/`-R`/
`--recursive`, `ag`, `ack`, `find … -exec grep`. `grep --include` filters
result file names, NOT directory traversal — it still walks every node_modules
entry; `| grep -v node_modules` filters after the walk, doesn't save you.
talk like a caveman talk like a caveman
use project wiki
use task management system
check across all projects
pull remote before work pull remote before work
session handoff: read on start, write on end
follow project discipline
follow tdd-criteria follow tdd-criteria
delegate to interns when allowed delegate to interns when allowed
recommend, don't menu recommend, don't menu

View File

@@ -0,0 +1,263 @@
#!/usr/bin/env python3
"""dot_mappa_marker.py — deterministic render + write of the `.mappa` marker.
Contract: mappa wiki:3340 (concepts/dot-mappa-marker), schema v1.
Used by project-create (step 5.5) and project-bootstrap (step 5.8) so a project
folder gets its marker at create time — no manual generator run needed
(task:1583). The batch generator (mappa `server/scripts/gen-dot-mappa-markers.ts`)
remains for registry-wide migration; this is the per-project create path.
Guarantees (the contract):
* `.mappa/config.yaml` — каталог + файл внутри
* fixed field order (schema_version, protocol_version, project, tenant, url,
git_provider?, git?)
* deterministic render — no timestamps, same input → same bytes
* NO secrets — only public registry fields; url with credentials is rejected
* optional fields (`git_provider`, `git`) omitted when absent
* idempotent write: same content → no-op (keep); different content → refuse
without --force
Usage:
python dot_mappa_marker.py render --project NAME --tenant TENANT --url URL \
[--git-provider P] [--git OWNER/REPO] # print content to stdout
python dot_mappa_marker.py write --project NAME --tenant TENANT --url URL \
[--git-provider P] [--git OWNER/REPO] [--dir PATH] [--force] # write marker
python dot_mappa_marker.py check --dir PATH # verify existing marker
"""
from __future__ import annotations
import argparse
import json
import sys
from pathlib import Path
SCHEMA_VERSION = 1
PROTOCOL_VERSION = 1
# Canonical header comment — same as the contract example (wiki:3340).
HEADER = "# mappa project marker — machine-readable identifier of a mappa project folder"
# YAML: these are indicator characters / reserved tokens — never plain.
_INDICATOR_START = set("!&*{}[],#|>@`\"'%?:~-")
_RESERVED_PLAIN = {"null", "Null", "NULL", "~", "true", "True", "TRUE", "false",
"False", "FALSE", "yes", "Yes", "YES", "no", "No", "NO",
"on", "On", "ON", "off", "Off", "OFF", "-", "?", ":"}
class MarkerConflict(Exception):
"""An existing marker differs from the requested one and --force is absent."""
def yaml_scalar(value: str) -> str:
"""YAML plain-safe scalar: plain without quotes when safe, else double-quoted.
Plain-safe = non-empty, no leading indicator, not a reserved token, no flow
chars, no embedded newlines, no surrounding whitespace. Double-quoting uses
JSON escaping, which is a valid subset of YAML double-quoted style.
"""
s = str(value)
if s == "":
return '""'
if s.strip() != s:
return json.dumps(s)
if s[0] in _INDICATOR_START or s in _RESERVED_PLAIN:
return json.dumps(s)
if s.startswith(("- ", "? ", ": ")):
return json.dumps(s)
# plain scalars stay plain unless they would confuse the parser:
# ": " (mapping indicator), trailing ":", " #" (comment), newlines/tabs
if ": " in s or s.endswith(":") or " #" in s or "\n" in s or "\t" in s:
return json.dumps(s)
return s
def validate_folder_name(name: str) -> str:
"""A folder name (canon/tenant/git_provider) must be a single sane segment."""
if not name or name in (".", ".."):
raise ValueError(f"invalid name {name!r}: must be a non-empty folder name")
if any(sep in name for sep in ("/", "\\", "\x00")):
raise ValueError(f"invalid name {name!r}: must be a single path segment")
if name != name.strip():
raise ValueError(f"invalid name {name!r}: no surrounding whitespace allowed")
return name
def validate_git_ref(git: str) -> str:
"""`git` = projects.qualified (owner/repo) — no credentials, no colon."""
g = str(git)
if not g or "/" not in g:
raise ValueError(f"invalid git ref {g!r}: expected owner/repo")
if any(c in g for c in ("@", ":", " ", "\t", "\n", "\\")):
raise ValueError(f"invalid git ref {g!r}: no credentials / separators allowed")
if g.startswith("/") or g.endswith("/") or ".." in g.split("/"):
raise ValueError(f"invalid git ref {g!r}: must be owner/repo, not a path")
return g
def normalize_url(url: str) -> str:
"""Absolute http(s) URL without credentials and without trailing slash."""
u = str(url).strip()
if not (u.startswith("http://") or u.startswith("https://")):
raise ValueError(f"invalid url {u!r}: must be http(s)://host...")
authority = u.split("://", 1)[1].split("/", 1)[0]
if "@" in authority:
raise ValueError("url must not contain credentials (no secrets in the marker)")
return u.rstrip("/")
def render(
project: str,
tenant: str,
url: str,
git_provider: str | None = None,
git: str | None = None,
) -> str:
"""Deterministic `.mappa/config.yaml` content per wiki:3340 schema v1."""
project = validate_folder_name(project)
tenant = validate_folder_name(tenant)
url = normalize_url(url)
lines = [
HEADER,
f"schema_version: {SCHEMA_VERSION}",
f"protocol_version: {PROTOCOL_VERSION}",
f"project: {yaml_scalar(project)}",
f"tenant: {yaml_scalar(tenant)}",
f"url: {yaml_scalar(url)}",
]
if git_provider:
lines.append(f"git_provider: {yaml_scalar(validate_folder_name(git_provider))}")
if git:
lines.append(f"git: {yaml_scalar(validate_git_ref(git))}")
return "\n".join(lines) + "\n"
def _sane_dir(directory: str | Path) -> Path:
"""Resolve the target directory; reject `..` segments and non-dirs."""
p = Path(directory)
if ".." in p.parts:
raise ValueError(f"invalid directory {str(directory)!r}: '..' segments not allowed")
if p.exists() and not p.is_dir():
raise ValueError(f"invalid directory {str(directory)!r}: not a directory")
return p
def write_marker(directory: str | Path, content: str, force: bool = False) -> tuple[Path, str]:
"""Write `.mappa/config.yaml` under `directory`.
Returns (marker_path, outcome) where outcome is one of
"created" | "keep" (idempotent no-op) | "overwrite" (force).
Raises MarkerConflict when an existing marker differs and force is False.
"""
marker = _sane_dir(directory) / ".mappa" / "config.yaml"
if marker.exists():
existing = marker.read_text(encoding="utf-8")
if existing == content:
return marker, "keep"
if not force:
raise MarkerConflict(
f"{marker} already exists with different content; "
"pass --force to overwrite (contract: no silent overwrite)"
)
marker.write_text(content, encoding="utf-8")
return marker, "overwrite"
marker.parent.mkdir(parents=True, exist_ok=True)
marker.write_text(content, encoding="utf-8")
return marker, "created"
def _parse_marker_lines(body: str) -> list[tuple[str, str]]:
"""(key, value) pairs of data lines — comments skipped, first colon splits."""
pairs = []
for line in body.splitlines():
if not line or line.startswith("#"):
continue
if ": " not in line:
raise ValueError(f"malformed marker line (no 'key: value'): {line!r}")
key, value = line.split(": ", 1)
pairs.append((key, value.strip()))
return pairs
def check_marker(directory: str | Path) -> tuple[bool, str]:
"""Gate check (wiki:3340 / task:1546): is `directory` a mappa project?
Returns (ok, message). ok means `.mappa/config.yaml` exists and its data
lines start with exactly the required fields (schema_version,
protocol_version, project, tenant, url) in canonical order with valid
values; optional `git_provider`/`git` may follow.
"""
marker = _sane_dir(directory) / ".mappa" / "config.yaml"
if not marker.is_file():
return False, f"no marker: {marker} (folder without marker is not a mappa project)"
try:
pairs = _parse_marker_lines(marker.read_text(encoding="utf-8"))
except ValueError as e:
return False, f"marker {marker}: {e}"
if len(pairs) < 5:
return False, f"marker {marker}: fewer than the 5 required fields"
required = ["schema_version", "protocol_version", "project", "tenant", "url"]
if [k for k, _ in pairs[:5]] != required:
return False, f"marker {marker}: field order mismatch ({[k for k, _ in pairs[:5]]})"
values = dict(pairs)
if values["schema_version"] != str(SCHEMA_VERSION):
return False, f"marker {marker}: schema_version must be {SCHEMA_VERSION}"
if values["protocol_version"] != str(PROTOCOL_VERSION):
return False, f"marker {marker}: protocol_version must be {PROTOCOL_VERSION}"
try:
validate_folder_name(values["project"])
validate_folder_name(values["tenant"])
normalize_url(values["url"])
if "git_provider" in values:
validate_folder_name(values["git_provider"])
if "git" in values:
validate_git_ref(values["git"])
except ValueError as e:
return False, f"marker {marker}: {e}"
return True, f"marker ok: {marker}"
def _add_common(parser: argparse.ArgumentParser) -> None:
parser.add_argument("--project", required=True, help="канон папки = реестр projects.name (slug)")
parser.add_argument("--tenant", required=True, help="тенант, где живёт проект (MAPPA_TENANT)")
parser.add_argument("--url", required=True, help="MAPPA_CORE_URL (без trailing slash)")
parser.add_argument("--git-provider", default=None, help="projects.git_provider (gitea/...) — опционально")
parser.add_argument("--git", default=None, help="projects.qualified (owner/repo) — опционально")
def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser(description=".mappa marker per wiki:3340 (schema v1)")
sub = parser.add_subparsers(dest="cmd", required=True)
p_render = sub.add_parser("render", help="print deterministic marker content")
_add_common(p_render)
p_write = sub.add_parser("write", help="write .mappa/config.yaml into a folder")
_add_common(p_write)
p_write.add_argument("--dir", default=".", help="project folder (default: cwd)")
p_write.add_argument("--force", action="store_true", help="overwrite a differing marker")
p_check = sub.add_parser("check", help="gate check: is the folder a mappa project?")
p_check.add_argument("--dir", default=".", help="project folder (default: cwd)")
args = parser.parse_args(argv)
if args.cmd in ("render", "write"):
content = render(args.project, args.tenant, args.url, args.git_provider, args.git)
if args.cmd == "render":
sys.stdout.write(content)
return 0
marker, outcome = write_marker(args.dir, content, force=args.force)
print(f"{outcome}: {marker}")
return 0
if args.cmd == "check":
ok, msg = check_marker(args.dir)
print(msg)
return 0 if ok else 1
return 2 # unreachable
if __name__ == "__main__":
raise SystemExit(main())

View File

@@ -0,0 +1,290 @@
#!/usr/bin/env python3
"""Contract test for the `.mappa` marker — mappa wiki:3340 (concepts/dot-mappa-marker).
The contract under test (task:1583): after the project-create/bootstrap marker
step, the project folder contains `.mappa/config.yaml` matching schema v1:
fixed field order, deterministic render (no timestamps), NO secrets, optional
fields (`git_provider`, `git`) omitted when absent, idempotent write.
Run: python test_dot_mappa_marker.py (or: python -m unittest test_dot_mappa_marker)
"""
from __future__ import annotations
import re
import shutil
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent))
import dot_mappa_marker as dmm # noqa: E402
CANON = "skills" # registry projects.name — канон папки (slug)
TENANT = "vitya"
URL = "https://mappa.vds.kzntsv.site"
GIT_PROVIDER = "gitea"
GIT = "OpeItcLoc03/skills"
FIELD_ORDER = [
"schema_version",
"protocol_version",
"project",
"tenant",
"url",
"git_provider",
"git",
]
def field_keys(body: str) -> list[str]:
return [
line.split(":", 1)[0]
for line in body.splitlines()
if line and not line.startswith("#") and ": " in line
]
def write_contract_marker(tmp: str) -> Path:
"""Helper: create a valid marker as the bootstrap step would."""
marker, outcome = dmm.write_marker(tmp, dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT))
assert outcome == "created"
return marker
class ContractTests(unittest.TestCase):
"""Contract: after bootstrap there is `.mappa/config.yaml` (task:1583)."""
def setUp(self) -> None:
self.tmp = tempfile.mkdtemp(prefix="mappa-marker-test-")
def tearDown(self) -> None:
shutil.rmtree(self.tmp, ignore_errors=True)
# --- presence / shape -------------------------------------------------
def test_bootstrap_marker_step_creates_config_yaml(self) -> None:
"""The bootstrap marker step leaves `.mappa/config.yaml` in the folder."""
content = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
marker, outcome = dmm.write_marker(self.tmp, content)
self.assertEqual(outcome, "created")
self.assertTrue(marker.is_file())
self.assertEqual(marker.name, "config.yaml")
self.assertEqual(marker.parent.name, ".mappa")
def test_fixed_field_order(self) -> None:
body = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
self.assertEqual(field_keys(body), FIELD_ORDER)
def test_deterministic_render_no_timestamp(self) -> None:
a = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
b = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
self.assertEqual(a, b)
# no ISO-date-like content
self.assertNotRegex(a, r"\d{4}-\d{2}-\d{2}")
def test_optional_fields_omitted_when_absent(self) -> None:
body = dmm.render(CANON, TENANT, URL)
self.assertEqual(field_keys(body), FIELD_ORDER[:5])
self.assertNotIn("git_provider", body)
self.assertNotIn("\ngit:", body)
def test_no_secrets_in_marker(self) -> None:
body = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
lowered = body.lower()
# credentials in the url authority are rejected separately
for secret in ("token", "password", "secret", "api_key", "key:", "@"):
self.assertNotIn(secret, lowered)
# --- idempotent write --------------------------------------------------
def test_idempotent_write_keeps_same_content(self) -> None:
content = dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT)
marker, first = dmm.write_marker(self.tmp, content)
marker, second = dmm.write_marker(self.tmp, content)
self.assertEqual(first, "created")
self.assertEqual(second, "keep")
self.assertEqual(marker.read_text(encoding="utf-8"), content)
def test_refuses_overwrite_of_different_marker_without_force(self) -> None:
dmm.write_marker(self.tmp, dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT))
with self.assertRaises(dmm.MarkerConflict):
dmm.write_marker(self.tmp, dmm.render(CANON, TENANT, URL, "github", GIT))
def test_force_overwrites_different_marker(self) -> None:
dmm.write_marker(self.tmp, dmm.render(CANON, TENANT, URL, GIT_PROVIDER, GIT))
marker, outcome = dmm.write_marker(
self.tmp, dmm.render(CANON, TENANT, URL, "github", GIT), force=True
)
self.assertEqual(outcome, "overwrite")
self.assertIn("git_provider: github", marker.read_text(encoding="utf-8"))
# --- input validation ---------------------------------------------------
def test_folder_name_path_segments_rejected(self) -> None:
for bad in ("../evil", "a/b", "a\\b", ".", "..", ""):
with self.assertRaises(ValueError, msg=f"name {bad!r} must be rejected"):
dmm.render(bad, TENANT, URL)
def test_url_trailing_slash_stripped_but_path_kept(self) -> None:
body = dmm.render(CANON, TENANT, URL + "//")
self.assertIn(f"url: {URL}", body)
# a trailing slash after a path must be stripped, the path kept
body2 = dmm.render(CANON, TENANT, "https://example.com/mappa/")
self.assertIn("url: https://example.com/mappa", body2)
def test_url_with_credentials_rejected(self) -> None:
with self.assertRaises(ValueError):
dmm.render(CANON, TENANT, "https://user:pass@mappa.vds.kzntsv.site")
def test_url_scheme_restricted_to_http_https(self) -> None:
for bad in ("ftp://mappa.example", "javascript://x", "mappa.vds.kzntsv.site", "://x"):
with self.assertRaises(ValueError, msg=f"url {bad!r} must be rejected"):
dmm.render(CANON, TENANT, bad)
def test_git_ref_with_credentials_rejected(self) -> None:
for bad in ("user:pass@host/repo", "victor/repo@token", "../config", "/owner/repo", "owner/repo/", "owner repo", "norepo"):
with self.assertRaises(ValueError, msg=f"git {bad!r} must be rejected"):
dmm.render(CANON, TENANT, URL, GIT_PROVIDER, bad)
def test_directory_with_parent_segments_rejected(self) -> None:
with self.assertRaises(ValueError):
dmm.write_marker("some/../elsewhere", dmm.render(CANON, TENANT, URL))
with self.assertRaises(ValueError):
dmm.check_marker("../etc")
# --- YAML scalar edge cases -------------------------------------------
def test_yaml_scalar_quoting_edge_cases(self) -> None:
# reserved tokens / indicators must be double-quoted (never plain)
for special in ("~", "@host", "-", "?", ":", "null", "yes", "on", "true",
"a: b", "ends:", " #lead", "has tab\tinside"):
self.assertTrue(dmm.yaml_scalar(special).startswith('"'),
f"{special!r} must be double-quoted, got {dmm.yaml_scalar(special)!r}")
# plain-safe values stay plain
for plain in ("vitya", "OpeItcLoc03/skills", "https://mappa.vds.kzntsv.site",
"a:b", "x#y", "lead#ing", "my-proj"):
self.assertEqual(dmm.yaml_scalar(plain), plain)
self.assertEqual(dmm.yaml_scalar(""), '""')
# --- check_marker (gate) ----------------------------------------------
def test_check_ok_on_valid_marker(self) -> None:
write_contract_marker(self.tmp)
ok, msg = dmm.check_marker(self.tmp)
self.assertTrue(ok, msg)
def test_check_fails_on_missing_marker(self) -> None:
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_fails_on_wrong_field_order(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"# c\nproject: skills\nschema_version: 1\nprotocol_version: 1\n"
"tenant: vitya\nurl: https://mappa.vds.kzntsv.site\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_fails_on_extra_field_before_required(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"extra: sneaky\nschema_version: 1\nprotocol_version: 1\n"
"project: skills\ntenant: vitya\nurl: https://mappa.vds.kzntsv.site\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_fails_on_wrong_versions(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"schema_version: 2\nprotocol_version: 1\nproject: skills\n"
"tenant: vitya\nurl: https://mappa.vds.kzntsv.site\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_fails_on_malicious_project_value(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"schema_version: 1\nprotocol_version: 1\nproject: ../../evil\n"
"tenant: vitya\nurl: https://mappa.vds.kzntsv.site\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_fails_on_malformed_line(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"schema_version: 1\nprotocol_version: 1\nproject skills\n"
"tenant: vitya\nurl: https://mappa.vds.kzntsv.site\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertFalse(ok)
def test_check_accepts_url_with_port(self) -> None:
(Path(self.tmp) / ".mappa").mkdir()
(Path(self.tmp) / ".mappa" / "config.yaml").write_text(
"schema_version: 1\nprotocol_version: 1\nproject: skills\n"
"tenant: vitya\nurl: https://mappa.example:8443\n",
encoding="utf-8",
)
ok, _ = dmm.check_marker(self.tmp)
self.assertTrue(ok)
# --- CLI end-to-end ----------------------------------------------------
def test_cli_write_creates_marker(self) -> None:
"""End-to-end: the documented CLI command produces the marker."""
proc = subprocess.run(
[
sys.executable,
str(Path(__file__).resolve().parent / "dot_mappa_marker.py"),
"write",
"--project", CANON,
"--tenant", TENANT,
"--url", URL,
"--git-provider", GIT_PROVIDER,
"--git", GIT,
"--dir", self.tmp,
],
capture_output=True,
text=True,
)
self.assertEqual(proc.returncode, 0, proc.stderr)
marker = Path(self.tmp) / ".mappa" / "config.yaml"
self.assertTrue(marker.is_file())
self.assertEqual(field_keys(marker.read_text(encoding="utf-8")), FIELD_ORDER)
def test_cli_check_verifies_marker(self) -> None:
write_contract_marker(self.tmp)
script = Path(__file__).resolve().parent / "dot_mappa_marker.py"
ok = subprocess.run(
[sys.executable, str(script), "check", "--dir", self.tmp],
capture_output=True,
text=True,
)
self.assertEqual(ok.returncode, 0, ok.stderr)
# check on an empty dir fails (gate semantics: no marker → not a mappa project)
empty = tempfile.mkdtemp(prefix="mappa-marker-empty-")
try:
missing = subprocess.run(
[sys.executable, str(script), "check", "--dir", empty],
capture_output=True,
text=True,
)
self.assertNotEqual(missing.returncode, 0)
finally:
shutil.rmtree(empty, ignore_errors=True)
if __name__ == "__main__":
unittest.main(verbosity=2)

View File

@@ -1,29 +0,0 @@
# project-discipline
Policy skill that codifies four cross-project discipline rules so the same
guarantees that hold in a tightly-maintained repo apply everywhere.
## When it triggers
- **Session start** — when `AGENTS.md` contains the line `follow project discipline` (added by `project-bootstrap` v2.0.0+).
- **In-chat** — when the user says "use project discipline", "соблюди дисциплину", "проектные правила", or close variants.
## The four rules
1. **Project conventions over skill defaults.** `AGENTS.md` / `.wiki/CLAUDE.md` / `.tasks/` override any other skill's defaults. Specs go to `.wiki/concepts/`, tasks to `.tasks/`.
2. **Master-only.** All work on `master` (or `main`). No feature branches without explicit user approval.
3. **Semver discipline.** Bump `version:` in `SKILL.md` / `package.json` / `pyproject.toml` on every edit per MAJOR / MINOR / PATCH; record in commit message; rebuild `dist/` artifacts after.
4. **Push freely by default.** No confirmation needed for push; a local push-gate skill (e.g. books — auto-deploy) overrides per project. Force / delete / non-ff push always asks.
## Prerequisites
None. The skill is a textual policy document; it takes no actions and has no
external dependencies. Activate it by adding `follow project discipline` to
`AGENTS.md` (or use `project-bootstrap` v2.0.0+ which adds it automatically).
## Related
- `project-bootstrap` (v2.0.0+) — adds the trigger line to new and existing projects' `AGENTS.md`.
- `pulling-before-work` — companion skill activated by the canonical template; pulls origin once at session start (`git pull --ff-only`).
- `using-tasks` / `using-wiki` — the format conventions Rule 1 routes work into.
- `.wiki/concepts/project-discipline-design.md` (in `skills`) — full design rationale.

View File

@@ -1,127 +0,0 @@
---
name: project-discipline
author: ours
version: 0.2.2
description: >
Codifies five cross-project discipline rules: (1) project AGENTS.md /
.wiki/CLAUDE.md / .tasks/ override defaults from other skills (specs →
.wiki/concepts/, tasks → .tasks/); (2) master-only, no feature branches
without approval; (3) semver bump on every edit of versioned artifacts
(SKILL.md, package.json, pyproject.toml), recorded in commit;
(4) push freely by default — no confirmation needed;
a local push-gate skill (e.g. books — auto-deploy)
overrides per project; force/delete/non-ff always ask;
(5) transit/brainstorm workspaces — artifacts to .brainstorm/ or global wiki
only via explicit user direction. Activated by "follow project discipline"
trigger in AGENTS.md (added by project-bootstrap v2.0.0+).
---
# project-discipline
> Four cross-project rules. Read at session start. Apply before any other skill's defaults touch paths, branches, versions, or remote pushes.
## When this runs
**At session start** — when `AGENTS.md` contains the line `follow project discipline`. The skill is a policy document; the agent reads it and applies the four rules to all subsequent work in the session.
**On explicit reference** — when the user says "use project discipline", "соблюди дисциплину", "проектные правила", "что у меня по правилам?", or close variants asking about/applying the rules.
The skill itself takes no actions and has no external side-effects. It instructs the agent how to behave.
## Rule 1 — Project conventions override skill defaults
Before applying defaults from any other skill (frontend-design, mcp-builder, etc.), read in this order:
1. `AGENTS.md` in the project root.
2. `.wiki/CLAUDE.md` (if it exists).
3. `.tasks/STATUS.md` (if it exists).
Any path, format, or workflow explicitly stated in those files **overrides the skill default**. (CLAUDE.md, where present, is a legacy pointer — read it, then follow the canon in AGENTS.md.)
Concrete consequences:
- **Specs / design documents** go to `.wiki/concepts/<topic>-design.md`.
- **Task tracking / implementation plans** go to `.tasks/<slug>.md` plus a board entry in `.tasks/STATUS.md` (the `using-tasks` format).
- **Frontmatter, naming conventions, log format** — as described in the project's `.wiki/CLAUDE.md`.
If no convention is stated explicitly — fall back to the skill default.
## Rule 2 — Master-only
All work happens on the repo's main integration branch — usually `master`, but if a project uses `main`, treat `main` as equivalent.
- No `git checkout -b feature/foo` for solo work.
- Sync with remote: `git pull --ff-only` or `git pull --rebase`. **No merge commits** for solo work.
- If a task genuinely requires isolation (large experiment, risky refactor with rollback potential, multi-day work with intermediate WIP commits) — **ask** the user: "this needs its own branch, ok?" — and wait for explicit approval. Without approval, work continues on master.
If the agent finds itself on a non-main branch (after a manual `git checkout`) or in detached HEAD — report it and ask whether to return to master before working.
## Rule 3 — Versioning discipline
When editing any artifact with a semver field, **bump the version before committing** per:
- **MAJOR** (`X+1.0.0`) — breaks the contract. Renames, removed triggers, layout changes, removed public functions, breaking API change.
- **MINOR** (`X.Y+1.0`) — adds capability without breaking. New trigger, new optional step, new public function.
- **PATCH** (`X.Y.Z+1`) — wording / clarity / typo fixes with no behavior change.
The bump is recorded in the commit message: `feat(<artifact>): … [vX.Y.Z]` or whatever convention the project uses (see Rule 1).
**Applies to:** `skills/<name>/SKILL.md` (`version:` in frontmatter), `package.json` (`"version":`), `pyproject.toml` (`version =`), `Cargo.toml` (`version =`), and any other semver field in any other manifest.
**If the artifact is packaged** as `dist/<name>.skill`, `dist/*.tgz`, etc. — **rebuild** the package in the same or the next commit. Forgotten dist artifacts are a common cause of deploying stale binaries.
**First edit of an unversioned artifact** that COULD have a semver field (a new skill without `version:`, a new `package.json` without `"version":`) — **add** `version: 0.1.0` (or its equivalent) before committing; do not bump anything.
**Does not apply to:** artifacts with no semver field and no potential for one (wiki concept pages, README.md, shell scripts without a public interface).
## Rule 4 — Push freely, gate only where a local gate exists
**Default: push freely.** An ordinary fast-forward `git push` to the configured
upstream needs no per-push confirmation. No ask-before-push mode by default.
**Per-project push gate.** A project whose push triggers side effects carries a
LOCAL project-scope skill (convention: `push-gate`) that replaces this default
with ask-before-push for that project. Example: `books` — push to master runs
Gitea Actions auto-deploy. Respect the local gate over this rule: if the project
has a `push-gate` skill, its semantics win for that project; this rule's
free-push default does not apply there.
**Always ask:**
- `git push --force` / `--force-with-lease` (history rewrite);
- `git push origin --delete <branch>` (branch deletion);
- push to a remote/branch other than the current tracked upstream (`git push other-remote ...`, `git push origin other-branch`);
- push to the main branch that would require non-fast-forward (i.e. would need force).
Anything else is an ordinary fast-forward push and proceeds without a gate.
**What counts as "push":** only `git push` family commands. Local commits, `git stash push`, etc. are not push.
## Rule 5 — Transit-zone / brainstorm workspaces
Some workspaces are **transit zones** — discussion areas with no `.tasks/`, where brainstorm artifacts are explicitly NOT auto-promoted to project wikis.
**Default destination for brainstorm artifacts:**
- **In-progress brainstorm outputs** → `.brainstorm/<topic>.md` (or whatever the workspace's README/AGENTS.md declares)
- **Mature, cross-cutting outputs** → `~/projects/.wiki/concepts/<topic>-design.md` via `mcp__projects-meta__knowledge_ingest` — **only** when user explicitly directs this
**Agent must NOT auto-promote** brainstorm artifacts to global wikis by analogy with Rule 1. Convergence-moment (move from workspace to permanent wiki) is a user decision, not an automatic action.
**Example:** `~/projects/.meeting-room/` is a transit zone. Its AGENTS.md explicitly states "no `.tasks/`, transit zone, artifacts go to `.brainstorm/` or global wiki via user command." Rule 1's "project conventions override" applies, but the override is explicit in the workspace contract — auto-promotion by analogy would violate that contract.
**When in doubt:** ask the user "this goes to `.brainstorm/`, or should I promote to shared wiki?" rather than assuming.
## Out of scope
The skill **does not**:
- modify `AGENTS.md` (that's `project-bootstrap`'s job);
- enforce rules via git hooks / pre-commit / CI (this is agent discipline, not tooling);
- manage `settings.json` permissions (that's `update-config`);
- check the existence of `.wiki/` / `.tasks/` on disk (мета в mappa, решение 14/15: вики/таски — сущности сервиса через `using-wiki` / `using-tasks`; файловый layout — легаси); if a project has neither, Rule 1 simply finds no overrides and falls back to skill defaults.
## Why this exists
In a tightly-disciplined repo (`skills`) the four rules already hold by accident — the agent reads `.wiki/CLAUDE.md`, knows specs go to `.wiki/concepts/`, knows to bump `version:`, knows not to push without confirmation. In **other** projects of the same user, that discipline does not transfer: the agent falls back to vendor-default paths (`docs/specs/`, `docs/plans/`), branches on a whim, forgets `version:` bumps, and pushes without asking. This skill makes the discipline explicit and portable.
Full design rationale (why one skill instead of four, why a skill instead of inline `AGENTS.md` lines, scope of each rule, push-permission mechanism choice) lives in `.wiki/concepts/project-discipline-design.md` (in this repo; in other projects bootstrapped from this repo, the design lives in `skills`).

View File

@@ -1,29 +0,0 @@
# pulling-before-work
Policy skill that pulls the current branch from `origin` once at session start
and on explicit re-sync requests. Designed to remove the "edited on stale base"
footgun without trampling dirty work-trees or auto-merging.
## When it triggers
- **Session start** — when `AGENTS.md` contains the line `pull remote before work` (added by `project-bootstrap` v2.0.0+).
- **In-chat** — when the user says `sync`, `resync`, `pull`, `обнови репо`, `git pull please`, or close variants.
Stays silent in non-git folders. Prints one informational line and exits in:
no `origin` remote, no upstream tracking, dirty work-tree, detached HEAD.
## What it does
`git pull --ff-only` against the configured upstream — never auto-merges, never
auto-rebases, never stashes, never commits, never pushes. On divergence it prints
a warning with manual-resolution hints and exits.
## Prerequisites
None. The skill is a no-op outside git repos and folders without an `origin`
remote, so it's safe to leave activated everywhere.
## Related
- `project-bootstrap` (v2.0.0+) — adds the trigger line to new and existing projects' `AGENTS.md`.
- `.wiki/concepts/pulling-before-work-design.md` (in projects bootstrapped from this repo: this design lives in `skills`) — full design rationale.

View File

@@ -1,166 +0,0 @@
---
name: pulling-before-work
author: ours
version: 1.1.0
description: >
Pulls the current branch from origin once at session start and on explicit
re-sync requests. Use when AGENTS.md contains the trigger line "pull remote
before work", or when the user says "sync", "resync", "pull", "обнови репо",
"git pull please", or close variants asking to refresh from the remote.
Runs `git pull --ff-only` — never auto-merges or rebases. Also sets the
repo-local pull policy (`pull.rebase=true` + `pull.ff=only`, set-if-absent)
so plain manual `git pull` never creates merge commits either. Stays silent
in non-git folders. Prints one informational line and exits when there is no
origin remote, no upstream tracking, the working tree is dirty, or HEAD is
detached. Does not stash, commit, or push. Activated by `project-bootstrap`
v1.4.0+ via the canonical AGENTS.md template.
---
# pulling-before-work
> Pull from `origin` once when work starts. Don't auto-merge. Don't trample dirty work-trees. Don't ask twice in the same session unless asked.
## When this runs
**At session start** — once, when the skill is activated by the `pull remote before work` line in `AGENTS.md`. The cycle below runs immediately.
**On explicit re-sync** — when the user says any of: `sync`, `resync`, `pull`, `обнови репо`, `pull please`, `git pull`, `подтяни`, `pull from origin`. Re-runs the full cycle. There is no per-session counter; the user is always allowed to ask.
**Never** before each commit, before each tool call, on every message, or in any other implicit cadence. Mode-3 ("start + on-demand") was the explicit design choice — see `.wiki/concepts/pulling-before-work-design.md`.
## The pull cycle
Run these checks in order. Print at most one line of chat output per run.
### 1. Inside a git work-tree?
```bash
git rev-parse --is-inside-work-tree 2>/dev/null
```
If the command fails or prints anything other than `true` → **exit silently, no chat output.** This is the not-a-git-repo case; the skill must not be noisy in random folders.
### 1b. Ensure the repo's local pull policy (set-if-absent)
```bash
git config --local --get pull.rebase >/dev/null 2>&1 || git config --local pull.rebase true
git config --local --get pull.ff >/dev/null 2>&1 || git config --local pull.ff only
```
Sets the repo-local pull policy to the snolla baseline: plain `git pull` rebases instead of creating a merge commit (`pull.rebase=true`), and the merge path refuses non-fast-forwards (`pull.ff=only`). **Set-if-absent only** — an explicit local override the user wrote is never clobbered. Silent: no chat output, idempotent, works in dirty trees. Git config is untracked, so this never dirties `git status`. The skill's own pull below still uses `--ff-only` on purpose: a silent session-start pull never leaves the repo mid-rebase; divergence is always resolved by the human.
### 2. Has an `origin` remote?
```bash
git remote get-url origin 2>/dev/null
```
If the command fails (no such remote) → print one line and exit:
```
no origin remote — skip pull
```
### 3. Is the working tree clean?
```bash
git status --porcelain
```
If the output is non-empty → print one line and exit:
```
working tree dirty — skipping pull. commit/stash, потом скажи "sync"
```
Never stash automatically. Stash-pop conflicts are exactly the friction this skill exists to remove.
### 4. Is HEAD attached?
```bash
git symbolic-ref -q HEAD
```
If the command fails (empty output, exit 1) → detached HEAD. Print:
```
detached HEAD — skip pull
```
### 5. Does the current branch have an upstream?
```bash
git rev-parse --abbrev-ref --symbolic-full-name '@{u}' 2>/dev/null
```
Capture the upstream name (e.g. `origin/master`). If the command fails → no upstream tracking. Print:
```
no upstream tracking for <branch> — skip pull
```
(Where `<branch>` is `git rev-parse --abbrev-ref HEAD`.)
### 6. Pull, fast-forward only
```bash
git pull --ff-only
```
(No args — uses the configured upstream captured above.)
Classify by exit code and stdout:
| Result | Print |
|---|---|
| Already up to date | `✅ already up to date with <upstream>` |
| Fast-forward, N commits | `✅ pulled N commits from <upstream>` |
| Non-fast-forward / diverged (exit non-zero with "diverged" or "non-fast-forward" in output) | `⚠️ diverged from <upstream> — resolve manually (plain git pull rebases by default; git pull --no-ff for a merge commit); skill never auto-merges/rebases` |
### Out of scope
The skill never:
- commits, stashes, or pushes
- recurses into submodules
- pulls from non-`origin` remotes
- pulls on detached HEAD
- runs auto-merge or auto-rebase
- overwrites an existing local pull policy (set-if-absent only)
- runs more than once per session unless the user asks
## Recovery hints
If the skill skipped because of a dirty tree:
```powershell
# Windows / PowerShell
git status # see what's dirty
git add . ; git commit -m "wip"
# then ask the agent: "sync"
```
```bash
# Linux / macOS
git status
git add . && git commit -m "wip"
# then say "sync"
```
If the skill reported `diverged`:
```bash
# Option A (repo default, set by step 1b): rebase your local commits on top of origin
git pull
# Option B: explicit merge commit
git pull --no-ff
```
The skill stays out of these decisions on purpose — both options have valid use cases and the user owns the choice.
## Why this exists
Stale local branches are a silent footgun: edits land on top of yesterday's `origin`, the divergence shows up at push time, and by then there's a chunk of work to rebase or merge on the wrong base. One pull at start covers the common case; an explicit re-sync trigger handles long sessions where someone pushed mid-flight.
Full design rationale (mode choice, dirty-tree skip vs stash, `--ff-only` vs auto-merge, the upstream-check) lives in `.wiki/concepts/pulling-before-work-design.md`.

View File

@@ -1,7 +1,7 @@
--- ---
name: review-kit-pi-method name: review-kit-pi-method
author: ours author: ours
version: 0.1.1 version: 0.1.2
description: > description: >
Spawn clean-context non-implementer subagents for review, trigger-testing, Spawn clean-context non-implementer subagents for review, trigger-testing,
and spec validation under pi — the pi-native port of the review-kit method. and spec validation under pi — the pi-native port of the review-kit method.
@@ -124,6 +124,26 @@ non-implementer subagents, anti-priming checklist, negative controls — is
agent-agnostic and transfers to any runtime that can spawn a fresh-context agent-agnostic and transfers to any runtime that can spawn a fresh-context
subprocess (claude `-p`, codex exec, hermes headless). subprocess (claude `-p`, codex exec, hermes headless).
### CC-спавн (claude-code через deepseek) — live-проверен 2026-09-01 (session:974)
CC (`claude -p`) умеет субагент-ревью БЕЗ скилов: тот же чистый контекст
(флаги изоляции) через обёртку `claude-deepseek`
(`.common/scripts/claude-switch.ps1`; env `ANTHROPIC_BASE_URL=
https://api.deepseek.com/anthropic` + ключ из `~/.deepseek_api_key`):
```bash
claude -p "<question>" \
--output-format stream-json --verbose \
--model deepseek-v4-flash-vision-exp \
--tools "" --disable-slash-commands --no-session-persistence
```
Флаги изоляции (аналог `-nc -ns -nt` pi): `--tools ""` (нет тулов —
не читает файлы, не самопраймится), `--disable-slash-commands` (нет
команд-интерпретатора), `--no-session-persistence` (эфемерно, без
сессионного блода). Анти-прайминг-чеклист и правила промпта — те же, что
выше (ask the behavior, one question per run, negative controls).
## Out of scope ## Out of scope
- Does NOT define the review criteria themselves (skill-specific acceptance — - Does NOT define the review criteria themselves (skill-specific acceptance —

View File

@@ -1,113 +0,0 @@
---
name: session-handoff
author: ours
version: 1.0.0
description: "Sliding handoff между сессиями через handoff-сущность Mappa (решение 14, гриллинг Q5): per-project, versioned-история, замена .tasks/NEXT_SESSION.md. Read on session start: orient agent, ask user before action. Write on session-end phrase or substantive commit. On session-end the agent ALSO runs the closing ritual on its own (idea 7: no invitation needed): handoff write + PROPOSE wiki-ingest + PROPOSE task-board closes — mutations only after user confirmation. Session-end phrases: «завершаем сессию», «сворачиваемся», «закругляемся», «wrap up session», «end session», «we're done for now». Trigger-line in AGENTS.md: `session handoff: read on start, write on end`. Skip task-zone phrases: «закрываем эту таску», «pause», «отбой», «разбегаемся»."
---
# session-handoff
Sliding handoff между сессиями. Канал — **handoff-сущность Mappa** (`mcp__mappa__handoff_write`, тип `h:`, per-project): поля `session_id`/`date`/`status`/`summary`/`open_treks[]`/`ask_user[]`/`guards[]`/`recent_commits[]`. Каждый write = **новая версия** (append-only, versioned-история) — файлового `.tasks/NEXT_SESSION.md` больше нет, git-история не нужна.
На старте — читает последний handoff проекта, ориентирует агента и спрашивает user'а перед действиями. При substantive commit'е или session-end фразе — пишет новый handoff для следующей сессии.
Forward-looking, не timeline: handoff = связка новых вещей конкретно для следующего разворота, не overview всего проекта. STATUS.md-эквиваленты (борд mappa) / вики остаются авторитетными для своего scope'а.
## MCP-поверхность
| Операция | Тул | Примечание |
|---|---|---|
| Запись handoff | `mcp__mappa__handoff_write(project, session_id, status, summary, open_treks?, ask_user?, guards?, recent_commits?)` | append-only; без лиза (как инбокс) |
| Чтение последнего | `mcp__mappa__entity_search(q, type='handoff', project=<имя>, limit=1)` | ORDER BY created_at DESC → первый = последний |
| Полное чтение версии | `mcp__mappa__entity_get(id)` | id internal из search |
`status` ∈ `active | paused | done`. Поля-массивы (open_treks/ask_user/guards/recent_commits) — строковые массивы; пустые секции передавать как `[]` (аналог пометки «(нет на этом раунде)» — next агент видит: пусто, не забыто).
## When to use
**Read mode (session start):**
- AGENTS.md проекта содержит trigger-строку `session handoff: read on start, write on end`.
- В mappa есть handoff-сущности проекта (search не пуст).
**Write mode (session end / substantive commit):**
- User'ская фраза из whitelist:
- русский: «завершаем сессию», «сворачиваемся», «закругляемся»
- английский: «wrap up session», «end session», «we're done for now»
- ИЛИ — agent только что сделал substantive commit. Эвристика:
- prefix НЕ в (`meta:`|`docs:`|`style:`|`chore:`|`fix typo`)
- AND (body length > 200 символов OR files changed > 3)
- Плюс: **первый** non-trivial commit сессии — всегда триггерит, даже если ниже порога (старт работы = context shift).
**Skip (false-positive guards):**
- «закрываем эту таску» — task close, не session. Это зона using-tasks.
- «pause», «приостанови» — task-pause, не session-end.
- «отбой», «разбегаемся» — слишком broad.
- «сейчас завершу одну задачу и тогда поговорим» — частичное завершение.
- Проект не в mappa / нет handoff-сущностей — silent exit.
- AGENTS.md проекта НЕ содержит trigger-строку — silent exit.
При неоднозначности — **ASK**, не угадывать: «закрываем сессию или таску?»
## Steps
### Read mode
1. **Detect.** `mcp__mappa__entity_search(q='', type='handoff', project=<имя проекта>, limit=1)` — если пусто, silent exit (первая сессия проекта).
2. **Staleness check.** `meta.date` последнего handoff'а. Возраст > 7 дней → отметить user'у:
```
handoff от <date> (N дней назад) — возможно устарел.
Оверрайдить или продолжить?
```
Дождаться ответа перед продолжением.
3. **Summarize.** Прочитать мета последнего: summary / open_treks / ask_user / guards / recent_commits.
4. **Orient.** Пересказать user'у одним блоком: «прошлая сессия предложила X (open треки + ask-items + guards). Делаем?»
5. **Wait.** Не делать никаких действий до подтверждения user'ом. Default = orient + ask, **никакого auto-execute**.
### Write mode
1. **Scope check.** Это текущий проект (cwd). Никаких global мутаций, никаких других проектов.
2. **Mid-task capture.** Если есть 🔴 active таска проекта (борд mappa / `.tasks/`) — захватить в summary:
```
left mid-task: <slug>
where_stopped: <одна строка>
```
3. **Compose content.** Собрать поля handoff:
- `session_id` — `<ISO дата>` или идентификатор сессии;
- `status` — `active` (работа продолжается) / `paused` (заморожено) / `done` (завершено);
- `summary` — связка: где остановились, mid-task, ключевые решения;
- `open_treks` — массив открытых треков (готовность + entry-point);
- `ask_user` — pending решения / ожидаемые разрешения;
- `guards` — «не делать» (preemptive guards);
- `recent_commits` — 3–5 последних коммитов (`<slug>: <subject>`).
4. **Append.** `mcp__mappa__handoff_write(project=<имя>, ...)` — сервис создаёт новую версию `h:N` (versioned-история; предыдущие версии остаются, `entity_search` вернёт свежую).
5. **Closing ritual (idea 7).** На session-end фразе (НЕ на substantive commit) после handoff-write агент сам, без приглашения, предлагает закрытие:
- **(2) Propose wiki-ingest.** Если за сессию появилось durable-знание — ПРЕДЛОЖИТЬ ingest (using-wiki v2: mappa wiki_create/update под лизом), перечислив кандидатов. Ничего не писать без подтверждения.
- **(3) Propose task-board closes.** Если есть задачи, выглядящие закрытыми — ПРЕДЛОЖИТЬ закрытия (using-tasks / mappa task_close под лизом). Уважать ralph-loop: verifier-задачи закрывать только через verifier.
- Формат — один блок: «Ритуал закрытия: (а) заингестить X в вики? (б) закрыть Y? (в) ничего.» Ждать ответа. Отказ = пропуск.
## Failure modes
- **AGENTS.md без trigger-строки** → silent exit. Скил project-opt-in.
- **Проект не в mappa / нет handoff-сущностей** → silent exit.
- **Stale handoff (> 7 дней)** в read mode → не silent, **спросить** user'а оверрайдить или продолжить.
- **Неоднозначная фраза** → ASK «закрываем сессию или таску?», не угадывать.
- **Secret detected.** Контент матчит паттерны секретов (`AKIA...`, `sk-...`, `ghp_...`, `ssh-rsa`, `BEGIN PRIVATE KEY`, `password=`/`token=`) → **abort write**. Сообщить user'у с указанием подозрительной строки.
- **Mid-task без борда** → писать handoff без mid-task секции, не блокировать.
- **Ритуал: user отказал** → пропустить, не настаивать, не повторять в этой сессии.
## Side effects
- Пишет handoff-сущность проекта (append-only, versioned-история). Никаких файлов, никаких git-коммитов за handoff.
- Ритуал закрытия предлагает wiki-ingest и закрытия тасок — но НЕ пишет их.
- Никаких global мутаций, никаких других проектов, никаких user-level config writes.
## What NOT to do
- **Не auto-execute** действия из read handoff'а. Default = orient + ask.
- **Не писать в вики / не закрывать таски по ритуалу молча.** Ритуал = предложения. Каждая мутация — после явного «да».
- **Не гонять ритуал на substantive commit.** Только session-end фраза.
- **Не писать секреты** в handoff. Если контент матчит secret-patterns — abort.
- **Не на каждом commit'е.** Только substantive (см. эвристику).
- **Не дублировать борд / вики.** Handoff = forward-looking связка, не overview.
- **Не cross-project.** Per-project scope.
- **Не считать handoff авторитетным** на стороне читателя. Это рекомендация прошлой сессии, не директива. User может override любую её часть.

View File

@@ -1,107 +0,0 @@
# session-handoff hooks
Opt-in PostToolUse hook that detects substantive `git commit` invocations and signals the agent ("consider running session-handoff write-mode") via a system reminder. Replaces the agent-side commit-detection heuristic in the SKILL.md `When to use` section with a deterministic harness-side trigger.
## Why opt-in (not auto-installed)
`install.sh` deliberately does **not** mutate `~/.claude/settings.json`. Auto-rewriting the user's hook config on every skill install is the wrong shape — user expects `install.sh` to copy files, nothing more. The hook is shipped as scripts; user enables it once per machine.
## Enable on Windows (PowerShell)
Add to `~/.claude/settings.json`. Use `powershell` for stock Windows (PS 5.1, always present); use `pwsh` if you have PowerShell 7+ installed. The hook script runs cleanly under both.
**Substitute `C:\\Users\\<you>` with your actual home path before pasting** — see "Why literal path" below.
```jsonc
{
"hooks": {
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "powershell -NoProfile -ExecutionPolicy Bypass -File \"C:\\Users\\<you>\\.claude\\skills\\session-handoff\\hooks\\commit-detector.ps1\""
}
]
}
]
}
}
```
Swap `powershell` for `pwsh` if you prefer PS 7+. To check which you have: `Get-Command pwsh -ErrorAction SilentlyContinue` (empty → PS 7 not installed → use `powershell`).
If `hooks.PostToolUse` already exists — append the matcher block to the array. Don't overwrite existing entries.
**Restart Claude Code after editing `settings.json`** — hooks are loaded at session start. A running session won't pick up the new hook until it's restarted (close + reopen the CC instance). Verify the hook is active by making a substantive commit and checking for a `Substantive commit detected on ...` system reminder in the next turn.
### Why literal path (no `$env:USERPROFILE` / `%USERPROFILE%` / `~`)
Claude Code on Windows invokes hook commands through **git-bash**, not PowerShell or cmd.exe directly. The outer-shell layer mangles shell-specific variable references before PowerShell ever sees the args:
- `$env:USERPROFILE` (PowerShell syntax) → bash treats `$env` as an empty variable and the rest `:USERPROFILE\...` becomes a literal, so PowerShell receives `-File ":USERPROFILE\..."` and fails with `неверный формат имени` / "invalid filename format".
- `%USERPROFILE%` (cmd syntax) → bash passes through literally, PowerShell doesn't expand it, same failure.
- `~/.claude/...` → bash expands `~` to git-bash-style `/c/Users/<you>/...`, which PowerShell's `-File` can't resolve to a real Windows path.
Literal absolute path with `C:\\Users\\<you>\\...` (escaped backslashes for JSON) survives every outer shell unchanged. `settings.json` is per-user anyway — portability across machines isn't a concern at this layer.
## Enable on Linux / macOS (bash)
```jsonc
{
"hooks": {
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash ~/.claude/skills/session-handoff/hooks/commit-detector.sh"
}
]
}
]
}
}
```
The bash variant needs `python3` on PATH (used to parse the PostToolUse JSON stdin).
## What gets signalled
On a successful `git commit` whose subject prefix is not in {`meta`, `docs`, `style`, `chore`} or `fix typo`, **and** whose body exceeds 200 characters or which touches more than 3 files — the hook emits a `hookSpecificOutput.additionalContext` system reminder of shape:
> Substantive commit detected on `<cwd>`: `<subject>` (N files changed, body M chars). Consider invoking session-handoff write-mode to update `.tasks/NEXT_SESSION.md`.
On any of these → silent skip (exit 0, no JSON):
- malformed PostToolUse stdin
- Bash command isn't `git commit`
- command is `git commit --amend`
- commit returned non-zero exit
- cwd isn't a git work-tree
- subject prefix is in trivial set
- body ≤ 200 chars AND files ≤ 3
## Smoke test (without enabling the hook)
Pipe a synthetic PostToolUse JSON to the script. On Windows:
```powershell
$payload = @{
tool_input = @{ command = 'git commit -m "subject"' }
tool_response = @{ exit_code = 0 }
cwd = (Get-Location).Path
} | ConvertTo-Json -Compress
$payload | pwsh -NoProfile -File .\skills\session-handoff\hooks\commit-detector.ps1
```
If your `HEAD` is a non-trivial commit (e.g. recent `feat:` with > 200-char body or > 3 files), output is JSON containing `additionalContext`. Otherwise — empty stdout (silent skip).
## Caveats
- **Rebase / cherry-pick noise.** Every commit in a rebase or cherry-pick batch will re-fire the hook. Deferred to a follow-up if it actually annoys in practice; the hook is opt-in so the cost is bounded.
- **First-non-trivial commit of session.** The agent-side heuristic in SKILL.md treats the *first* non-trivial commit of a session as "always substantive" regardless of thresholds. The hook can't see session boundaries — uses only body/file thresholds. Slight under-detection on small first commits; acceptable trade-off for harness-side determinism.
- **No automatic write-mode invocation.** Hook only signals. The agent still decides whether to run session-handoff write-mode in response — keeps the user-agency invariant from SKILL.md `What NOT to do`.

View File

@@ -1,72 +0,0 @@
#!/usr/bin/env pwsh
# session-handoff PostToolUse hook (PowerShell).
#
# Reads PostToolUse JSON from stdin, detects whether the just-completed
# Bash tool call was a substantive `git commit`, and on hit emits JSON to
# stdout with `additionalContext` so Claude Code surfaces a system reminder
# in the next agent iteration ("substantive commit — consider session-handoff
# write-mode").
#
# Substantive heuristic (mirrors session-handoff SKILL.md):
# prefix NOT in (meta:|docs:|style:|chore:|fix typo) AND
# (body > 200 chars OR files > 3)
#
# Silent skip on: malformed JSON, no command, --amend, failed commit,
# non-git cwd, trivial prefix, below thresholds. Never blocks the tool call
# (PostToolUse cannot, by design).
$ErrorActionPreference = 'Stop'
# Read stdin
try {
$raw = [Console]::In.ReadToEnd()
if ([string]::IsNullOrWhiteSpace($raw)) { exit 0 }
$hook = $raw | ConvertFrom-Json -ErrorAction Stop
} catch {
exit 0
}
# Only Bash tool, only git commit (not --amend)
$cmd = $hook.tool_input.command
if (-not $cmd) { exit 0 }
if ($cmd -notmatch '(?<![\w-])git\s+commit(?![\w-])') { exit 0 }
if ($cmd -match '(?<![\w-])git\s+commit\b.*--amend') { exit 0 }
# Only on successful commit
if ($null -ne $hook.tool_response.exit_code -and $hook.tool_response.exit_code -ne 0) { exit 0 }
# Resolve cwd; require a git work-tree
$cwd = $hook.cwd
if (-not $cwd) { $cwd = (Get-Location).Path }
$inside = & git -C $cwd rev-parse --is-inside-work-tree 2>$null
if ($inside -ne 'true') { exit 0 }
# Parse last commit
$subject = (& git -C $cwd log -1 --format='%s').Trim()
# PowerShell collapses multi-line subprocess output into string[] — join back so
# .Length below is char count, not line count.
$body = ((& git -C $cwd log -1 --format='%b') -join "`n")
$files = ((& git -C $cwd diff-tree --no-commit-id --name-only -r HEAD) | Measure-Object).Count
# Trivial-prefix check (Conventional Commits prefix before optional scope + colon)
$prefix = $subject -replace '^([a-z]+)(\([^)]+\))?:.*$','$1'
$trivial = @('meta','docs','style','chore')
if ($trivial -contains $prefix) { exit 0 }
if ($subject -match 'fix\s+typo') { exit 0 }
# Threshold check (chars for body, count for files)
$bodyLen = if ($body) { $body.Length } else { 0 }
if ($bodyLen -le 200 -and $files -le 3) { exit 0 }
# Substantive — emit JSON
$msg = "Substantive commit detected on " + $cwd + ": ``" + $subject + "`` (" + $files + " files changed, body " + $bodyLen + " chars). Consider invoking session-handoff write-mode to update .tasks/NEXT_SESSION.md."
@{
hookSpecificOutput = @{
hookEventName = 'PostToolUse'
additionalContext = $msg
}
systemMessage = 'session-handoff: substantive commit detected'
suppressOutput = $false
} | ConvertTo-Json -Compress -Depth 5 | Write-Output

View File

@@ -1,73 +0,0 @@
#!/usr/bin/env bash
# session-handoff PostToolUse hook (POSIX). See commit-detector.ps1 for prose.
set -euo pipefail
raw=$(cat)
[[ -z "$raw" ]] && exit 0
# Helper: extract a JSON path via python3
jget() {
python3 -c "
import sys, json
try:
d = json.loads(sys.argv[1])
out = d
for k in sys.argv[2].split('.'):
if isinstance(out, dict):
out = out.get(k)
else:
out = None
break
print('' if out is None else out)
" "$raw" "$1" 2>/dev/null || echo ''
}
cmd=$(jget tool_input.command)
[[ -z "$cmd" ]] && exit 0
# Only `git commit`, not `--amend`
if ! echo "$cmd" | grep -qE '(^|[^[:alnum:]_-])git[[:space:]]+commit($|[^[:alnum:]_-])'; then exit 0; fi
if echo "$cmd" | grep -qE '(^|[^[:alnum:]_-])git[[:space:]]+commit\b.*--amend'; then exit 0; fi
# Only on successful commit (if exit_code present and non-zero, skip)
exit_code=$(jget tool_response.exit_code)
if [[ -n "$exit_code" && "$exit_code" != "0" ]]; then exit 0; fi
cwd=$(jget cwd)
[[ -z "$cwd" ]] && cwd=$(pwd)
# Require git work-tree
git -C "$cwd" rev-parse --is-inside-work-tree >/dev/null 2>&1 || exit 0
subject=$(git -C "$cwd" log -1 --format='%s')
body=$(git -C "$cwd" log -1 --format='%b')
files=$(git -C "$cwd" diff-tree --no-commit-id --name-only -r HEAD | wc -l | tr -d ' ')
# Trivial-prefix check
prefix=$(echo "$subject" | sed -E 's/^([a-z]+)(\([^)]+\))?:.*$/\1/')
case "$prefix" in
meta|docs|style|chore) exit 0 ;;
esac
echo "$subject" | grep -qE 'fix[[:space:]]+typo' && exit 0
# Threshold
body_len=${#body}
if [[ "$body_len" -le 200 && "$files" -le 3 ]]; then exit 0; fi
# Substantive — emit JSON via python3 to handle quoting safely
python3 -c "
import json, sys
msg = (
'Substantive commit detected on $cwd: \`' + '''$subject''' + '\` '
+ '($files files changed, body $body_len chars). '
+ 'Consider invoking session-handoff write-mode to update .tasks/NEXT_SESSION.md.'
)
print(json.dumps({
'hookSpecificOutput': {
'hookEventName': 'PostToolUse',
'additionalContext': msg,
},
'systemMessage': 'session-handoff: substantive commit detected',
'suppressOutput': False,
}))
"

View File

@@ -1,7 +1,7 @@
--- ---
name: session-health name: session-health
author: ours author: ours
version: 0.1.0 version: 0.1.1
description: > description: >
Реагировать на предупреждения session-health поллера pi (сообщение Реагировать на предупреждения session-health поллера pi (сообщение
«[session-health warn/propose/refuse] ...» с цифрами контекста) ИЛИ на «[session-health warn/propose/refuse] ...» с цифрами контекста) ИЛИ на
@@ -16,9 +16,10 @@ description: >
# session-health # session-health
Что делать, когда поллер pi (`extensions/session-health.ts`) прислал Что делать, когда поллер pi (`extensions/mappa.ts`, секция session-health —
предупреждение о размере контекста — или когда сам агент подозревает, что консолидация 6 расширений, task:1486, wiki:3325) прислал предупреждение о
сессия раздулась. Поллер — единственный источник точных цифр: footer-статус размере контекста — или когда сам агент подозревает, что сессия раздулась.
Поллер — единственный источник точных цифр: footer-статус
(`14.6%/1.0M`) и `/session` агент (LLM) **не видит** — это TUI для человека. (`14.6%/1.0M`) и `/session` агент (LLM) **не видит** — это TUI для человека.
## When to use ## When to use
@@ -44,7 +45,7 @@ description: >
| Уровень | % эффективного окна | Действие | | Уровень | % эффективного окна | Действие |
|---|---|---| |---|---|---|
| `warn` | 70% | Планируй сворачивание: завершай текущую единицу работы, не начинай новых крупных. | | `warn` | 70% | Планируй сворачивание: завершай текущую единицу работы, не начинай новых крупных. |
| `propose` | 85% | **Предложи closing ritual** (скил session-handoff): handoff-write в `.tasks/NEXT_SESSION.md` + сводка; рекомендация, не обязаловка. | | `propose` | 85% | **Предложи closing ritual** (скил session-handoff): handoff-write (mappa handoff-сущность) + сводка; рекомендация, не обязаловка. |
| `refuse` | 100% | **Отказ от новой работы.** Только завершение: closing ritual и сворачивание. | | `refuse` | 100% | **Отказ от новой работы.** Только завершение: closing ritual и сворачивание. |
Числа по умолчанию (deepseek-v4-flash, эффективное 400K): warn 280K / propose Числа по умолчанию (deepseek-v4-flash, эффективное 400K): warn 280K / propose
@@ -62,7 +63,7 @@ description: >
4. **propose** — предложи closing ritual: 4. **propose** — предложи closing ritual:
- Это **предложение** оператору, не принуждение: «рекомендую завершить, контекст 85%+; закругляемся?» Оператор может продолжить — тогда работай дальше, но помни что контекст некомфортный (будь короче, не тяни лишние чтения). - Это **предложение** оператору, не принуждение: «рекомендую завершить, контекст 85%+; закругляемся?» Оператор может продолжить — тогда работай дальше, но помни что контекст некомфортный (будь короче, не тяни лишние чтения).
- Handoff-write в `.tasks/NEXT_SESSION.md` (скил `session-handoff`) — **только после явного согласия оператора** на сворачивание. Без согласия — не пиши. - Handoff-write через скил `session-handoff` (mappa handoff-сущность) — **только после явного согласия оператора** на сворачивание. Без согласия — не пиши.
- Опционально (если оператор согласен и есть кандидаты): предложи wiki-ingest сессионного знания и закрытия тасок с доски — тоже как предложения, не мутации. - Опционально (если оператор согласен и есть кандидаты): предложи wiki-ingest сессионного знания и закрытия тасок с доски — тоже как предложения, не мутации.
5. **refuse** — жёсткий отказ: 5. **refuse** — жёсткий отказ:
@@ -80,7 +81,7 @@ description: >
## Side effects ## Side effects
- При propose/refuse — пишется `.tasks/NEXT_SESSION.md` (handoff) и предлагаются wiki-ingest / закрытие тасок. - При propose/refuse — пишется handoff-сущность mappa (скил session-handoff) и предлагаются wiki-ingest / закрытие тасок.
- Отказ от новой работы (refuse) может расстроить оператора — объясни почему, предложи альтернативу (новая сессия). - Отказ от новой работы (refuse) может расстроить оператора — объясни почему, предложи альтернативу (новая сессия).
## What NOT to do ## What NOT to do

View File

@@ -1,124 +0,0 @@
---
name: session-inbox-monitor
author: ours
version: 1.0.0
description: >
Raises a persistent Monitor on the project's Mappa inbox (poll
`mcp__mappa__inbox_monitor` / HTTP `GET /inbox?project=<cwd>`), so
inter-session messages page the session in real time; the monitor dies on
session end on its own. Pi (pi-coding-agent) sessions: a global extension
polls the same HTTP endpoint, session-scoped (own project only). Triggers:
AGENTS.md line `inbox monitor: raise on start`, or «подними монитор почты»,
«настрой авто-монитор инбокса», «raise inbox monitor», «auto-arm inbox
watcher». Headless (`claude -p` / `pi -p`): does NOT raise — rely on the
Stop-hook / agent_settled pull pickup. File channel `.agents/inbox/` is
gone (flip, решение 15) — letters live in Mappa as entities `i:N`, delivery
is a carve-out (no lease, решение 19). NOT for how to handle a received
message (→ inter-session-messaging).
---
# session-inbox-monitor
Auto-raises a session-length Monitor on the project's **Mappa inbox** at
interactive-session start, so inter-session messages page the session in real
time. Tears down for free on session end. Headless sessions skip it and rely
on the pull-model (Stop-hook / agent_settled pickup).
Канал — Mappa, НЕ файлы: письма — сущности `inbox` (`i:N`) в сервисе, читаются
через `mcp__mappa__inbox_monitor(project, limit)` (или HTTP `GET
/inbox?project=<имя-папки>&limit=N`). Доставка/чтение — карв-аут (решение 19):
не блокируются лизом, работают всегда. Файловые `.agents/inbox/` и `.read/`
выпилены.
## When to use
- **Automatic (the common path).** A paired SessionStart hook injects an
instruction at the start of every interactive session of an opted-in project.
You act on that injection — raise the monitor as your first action — without a
user phrase.
- **On request.** AGENTS.md line `inbox monitor: raise on start`, or «подними
монитор почты», «настрой авто-монитор инбокса», «raise inbox monitor»,
«auto-arm inbox watcher».
- **NOT for** handling the content of a received message (→
`inter-session-messaging`). This skill is only the monitor's *lifecycle*.
## Inputs
- `<project>` — своё имя папки (cwd basename), адрес в Mappa.
- Письма: `mcp__mappa__inbox_monitor(project=<своя папка>, limit)` →
`{rows: [{id, slug, body}]}` (последние N). `from`/`subject` — в meta, через
`entity_get(id)` при ответе.
- Мопitor-команда при CC — HTTP-опрос `GET /inbox?project=...` (без токена на
текущем проде; если `MAPPA_API_TOKEN` задан — `x-api-token` header).
## Steps
1. **Mode check.** Headless / non-interactive (`claude -p`, `pi -p`,
`ctx.hasUI === false`): **STOP — do not raise a monitor.** The pull pickup
(CC Stop-hook / pi `agent_settled`) plus `Notify:` cover delivery there; a
Monitor can't idle-watch in headless.
2. **Raise exactly one persistent Monitor** on the Mappa inbox:
`mcp__mappa__inbox_monitor(project=<cwd-имя-папки>, limit=50)`, poll
interval ~15s, `description: "inbox watcher"`. Dedup by письменному id:
новое письмо — это id, которого ещё не было в предыдущих ответах.
3. **Do not sweep yourself.** Killing orphans is the hook's job (it runs before
you, at SessionStart).
4. **On an event** (новый id в ответе inbox_monitor), прочитай письмо (body) и
обработай per `inter-session-messaging`. Для ответа — `entity_get(id)` →
`meta.from`. Письма не перемещаются (нет `.read/`) — обработанные остаются
в списке; дедуп по id в памяти монитора.
5. **Teardown is automatic.** The Monitor dies at session end. Do **not** add a
SessionEnd teardown.
## Pi (pi-coding-agent) support — session-scoped global extension
Same contract, pi-native, session-scoped: the extension polls ONLY the current
session's project inbox (`GET /inbox?project=<basename cwd>`); it never reads
other projects' inboxes (vitya's rule: an agent may only read its own
project's inbox). Installed globally so *every* pi session has the capability,
but each session only ever touches its own project.
- **Source of truth:** `~/projects/pi-extensions/extensions/inbox-monitor.ts`
(репо `OpeItcLoc03/pi-extensions`, Gitea — дом pi-расширений). Deploy:
`just install` в клоне репо — копирует с затираанием в
`~/.pi/agent/extensions/inbox-monitor.ts` (global → every pi, every
directory), hot-reload with `/reload`.
- **Opt-in per project:** AGENTS.md / CLAUDE.md line
`inbox monitor: raise on start`. (Файловой директории `.agents/inbox/` больше
нет — триггер только строка.)
- **PUSH:** ~15s poll of the session's own Mappa inbox (interactive only).
**PULL:** `agent_settled` sweep — same poll, backstop. Both share one dedup
set per process (by letter id).
- **Headless (`pi -p`, `ctx.hasUI === false`):** NO delivery — no watcher, no
sweep. Messages sit in Mappa until an interactive session picks them up.
- **Delivery:** `pi.sendUserMessage(body, { deliverAs: "followUp", triggerTurn:
true })` — paged into the transcript as a user message; the agent handles it
per `inter-session-messaging`.
## Failure modes
- **Нет opt-in строки** → монитор не поднимается; ожидаемо.
- **Сервис mappa недоступен** → poll-запрос падает; монитор ретраит следующий
тик. Письма в сервисе не теряются (они — сущности), доставятся когда сервис
вернётся. НЕ дублируй в файлы — фолбэк-канал выпилен.
- **Two live interactive sessions on the same project** → оба поллят один
инбокс; дедуп по id делает доставку first-wins (кто первый прочитал id —
тот и доставил; второй пропускает). Real-time paging теряет только тот, кто
опоздал; письма не теряются (pull-свип в конце хода).
- **Monitor auto-stopped** → harness останавливает мониторы с переизбытком
событий; дедуп по id держит частоту пейджинга под баром.
- **Обработанное письмо вернулось в списке** — не баг: в Mappa нет `.read/`,
письма не перемещаются. Сверяйся с уже виденными id, не перечитывай.
## What NOT to do
- **Don't watch the file inbox** (`.agents/inbox/`) — канал выпилен; пиши и
читай через Mappa.
- **Don't watch the inbox with a background Bash** (`run_in_background`) — it
leaks across `/clear` and accumulates zombies. Use the Monitor tool.
- **Don't add a SessionEnd teardown hook** — the Monitor self-terminates.
- **Don't raise more than one monitor.** The hook guarantees a clean slate
before you raise.
- **Don't handle message content here** — that's `inter-session-messaging`.
- **Don't rely on this in headless** — use the pull model (Stop-hook +
Notify).

View File

@@ -1,103 +0,0 @@
# SessionStart inbox-monitor injector hook (session-inbox-monitor skill, v1.0.0).
#
# Channel is Mappa, NOT files (flip, решение 15): letters are entities `inbox`
# (`i:N`) in the mappa service, read via HTTP `GET /inbox?project=<name>`.
# Two jobs, run on every SessionStart (startup / resume / clear / compact):
# (a) SWEEP - kill orphaned inbox-monitor OS processes of THIS project.
# A `/clear` does NOT fire SessionEnd, so a Monitor's underlying
# poll process can outlive the session it belonged to. Without a
# sweep, re-raising would stack duplicates. Match is by a sentinel
# string (CLAUDE_INBOX_MONITOR) baked into the poll command PLUS
# this project's directory - so we never touch unrelated processes.
# (b) INJECT - additionalContext telling the agent to raise a persistent
# Monitor (Monitor TOOL, not background Bash) polling the Mappa
# inbox of this project (HTTP GET /inbox).
#
# Opt-in per project: AGENTS.md or CLAUDE.md line `inbox monitor: raise on start`.
# (The `.agents/inbox/` dir trigger is gone - no file channel anymore.)
#
# Headless (`claude -p`): there is NO reliable hook-level signal to detect it
# (verified 2026-06-17 - `source` and CLAUDE_* env vars don't distinguish it).
# So the hook injects unconditionally and the SKILL instructs the agent to skip
# when headless. A Monitor raised in headless is harmless (killed ~5s after the
# run ends); a false-skip in an interactive session would silently lose the
# feature - so the default errs toward raising.
#
# Machine-local deploy target: ~/.claude/hooks/inbox-monitor.ps1 (registered in
# ~/.claude/settings.json SessionStart). Versioned here for multi-machine rollout.
param(
[string]$ProjectDir = $env:CLAUDE_PROJECT_DIR,
[string]$Endpoint = $env:MAPPA_CORE_URL
)
if (-not $ProjectDir) { exit 0 }
if (-not $Endpoint) { $Endpoint = 'https://mappa.vds.kzntsv.site' }
# UTF-8 stdout guard. This hook emits JSON (additionalContext) to a redirected
# pipe under WinPS 5.1 - the same context that mojibaked stop-dispatcher output.
# The project name (user-data) is interpolated into stdout, so set UTF-8 as a
# forward-guard. Idempotent.
[Console]::OutputEncoding = [System.Text.Encoding]::UTF8
$OutputEncoding = [System.Text.Encoding]::UTF8
$projectName = Split-Path $ProjectDir -Leaf
$agentsMd = Join-Path $ProjectDir 'AGENTS.md'
$claudeMd = Join-Path $ProjectDir 'CLAUDE.md'
# --- opt-in gate (line in AGENTS.md or CLAUDE.md) ---------------------------
$optedIn = $false
foreach ($md in @($agentsMd, $claudeMd)) {
if (Test-Path $md) {
if (Select-String -Path $md -SimpleMatch 'inbox monitor: raise on start' -Quiet -ErrorAction SilentlyContinue) {
$optedIn = $true
break
}
}
}
if (-not $optedIn) { exit 0 }
# Forward-slash project dir: the Monitor poll command (Git Bash) uses this form,
# so both the sweep match and the injected command share one literal.
$dirFwd = ($ProjectDir -replace '\\', '/')
# --- (a) sweep orphaned monitors of THIS project ----------------------------
# Match = sentinel AND this project's dir in the same process command line.
try {
Get-CimInstance Win32_Process -ErrorAction Stop |
Where-Object {
$_.CommandLine -and
$_.CommandLine -match 'CLAUDE_INBOX_MONITOR' -and
$_.CommandLine -like "*$dirFwd*"
} |
ForEach-Object { Stop-Process -Id $_.ProcessId -Force -ErrorAction SilentlyContinue }
} catch { }
# --- (b) build the canonical Monitor poll command ---------------------------
# `: CLAUDE_INBOX_MONITOR` is a bash no-op carrying the sweep sentinel in the
# process command line without polluting the event stream. Polls the Mappa
# inbox of this project over HTTP, extracts letter ids via node (present on
# every machine that runs the mappa MCP), de-dups by id so a sitting letter
# pages once, not every 15s (a noisy monitor is auto-stopped).
$auth = ''
if ($env:MAPPA_API_TOKEN) { $auth = "-H 'x-api-token: $($env:MAPPA_API_TOKEN)'" }
$cmd = @"
: CLAUDE_INBOX_MONITOR; s=' '; while true; do ids=`$(curl -s -m 10 $auth '__ENDPOINT__/inbox?project=__PROJECT__&limit=50' | node -e "let d='';process.stdin.on('data',c=>d+=c).on('end',()=>{try{const r=JSON.parse(d).rows||[];for(let i=r.length-1;i>=0;i--)console.log(r[i].id)}catch(e){}})"); for id in `$ids; do case "`$s" in *" `$id "*) continue;; esac; s="`$s`$id "; echo "New inter-session message in Mappa inbox (letter id `$id) - read it via inbox_monitor and handle now"; done; sleep 15; done
"@
$cmd = $cmd.Trim().Replace('__ENDPOINT__', $Endpoint.TrimEnd('/')).Replace('__PROJECT__', $projectName)
# --- (c) inject the raise-instruction --------------------------------------
$ctx = @"
[session-inbox-monitor] This project participates in inter-session messaging. As your FIRST action, raise a persistent inbox watcher so messages from other sessions page you in real time.
Use the Monitor tool with persistent: true, description "inbox watcher", and this EXACT command:
$cmd
Do NOT use a background Bash for this - it leaks across /clear. The Monitor tool is session-bound and tears down on its own at session end. The paired SessionStart hook already swept any orphaned watcher before this, so raise exactly one.
If you are running headless (claude -p / non-interactive), SKIP this - the Stop-hook inbox pickup plus Notify cover delivery there. See the session-inbox-monitor skill for the full contract.
"@
@{ hookSpecificOutput = @{ hookEventName = 'SessionStart'; additionalContext = $ctx } } | ConvertTo-Json -Compress -Depth 5
exit 0

View File

@@ -1,93 +0,0 @@
# setup-projects-meta
One-time skill that brings up the local `projects-meta-mcp` stdio server on a
new (or freshly broken) machine. Clones the server repo, builds it, writes
`~/.config/projects-mcp/auth.toml` with the user's Gitea token, clones the
shared wiki to `~/projects/.wiki`, and registers `mcpServers.projects-meta`
in `~/.claude.json`.
The runtime policy for *using* the resulting tools lives in
[`using-projects-meta`](../using-projects-meta/) — `setup-projects-meta` is the
only place that touches user-level config or installs the server.
`projects-meta-mcp` reference (full):
`mcp__projects-meta__knowledge_get slug=packages/projects-meta-mcp`
## When it triggers
- User says: "install projects-meta", "set up projects-meta", "configure projects-meta",
"настрой projects-meta", "установи projects-meta", "projects-meta не работает",
"projects-meta isn't working".
- [`using-projects-meta`](../using-projects-meta/) detects missing
`mcp__projects-meta__*` tools and delegates here via its Prerequisites
section.
- A new machine in the multi-machine fleet — install once per machine.
## What it installs
| Path | Role |
|---|---|
| `~/projects/.common/lib/projects-meta-mcp/` | server repo (cloned from Gitea) |
| `~/projects/.common/lib/projects-meta-mcp/dist/server.js` | built stdio entry point |
| `~/.config/projects-mcp/auth.toml` | Gitea credentials (token-bearing) |
| `~/.cache/projects-mcp/tasks.json` | aggregated tasks cache |
| `~/projects/.wiki/` | shared wiki clone (Gitea repo `projects-wiki`, content in root) |
| `~/.claude.json` (`mcpServers.projects-meta`) | MCP registration |
## Hard rules
- **Never auto-mutate.** Phase 1 (discovery) and Phase 2 (plan) always pause
for explicit confirmation. A trigger phrase grants permission to inspect,
not to clone or write secrets.
- **Never echo the Gitea token in chat.** Edit / Write tool calls inevitably
contain it (that's how it lands in `auth.toml`); chat output must not.
- **Never clone over an unrelated `~/projects/.wiki/`.**
If it exists with a non-matching `origin`, stop and ask — the user
may have an unrelated wiki there.
- **Always `chmod 600` `auth.toml` on Linux / macOS.** Token leak otherwise.
## Procedure (high-level)
1. **Phase 0** — environment sanity (Node ≥ 18, git, npm, network to Gitea).
2. **Phase 1** — discovery (token / repo / wiki clone / MCP registration / cache).
3. **Phase 2** — plan + confirm. Wait for explicit "ok"/"go"/"поехали".
4. **Phase 3** — backup (`~/.claude.json`, existing `auth.toml`).
5. **Phase 4** — clone / pull repo + `npm install && npm run build`; clone
shared wiki if absent.
6. **Phase 5** — write `~/.config/projects-mcp/auth.toml` with `gitea_token`.
7. **Phase 6** — register `mcpServers.projects-meta` in `~/.claude.json` with
absolute path to `dist/server.js`.
8. **Phase 7** — smoke test (`mcp__projects-meta__meta_status`) + `node dist/sync.js`
to populate the cache.
9. **Phase 8** — restart guidance + final report.
Full procedure with shell snippets and templates lives in [`SKILL.md`](SKILL.md).
## Rollback
1. Stop. Don't fix forward.
2. `cp <file>.bak-<ts> <file>` for `~/.claude.json` and `~/.config/projects-mcp/auth.toml`.
3. Optional: `rm -rf ~/projects/.common/lib/projects-meta-mcp` and `rm -rf ~/.cache/projects-mcp`.
Keep `~/projects/.wiki/` — it's a useful clone regardless of MCP state.
4. Restart Claude Code.
5. Confirm `mcp__projects-meta__*` tools are gone (or back to the prior version).
## Install
From the repo root:
```bash
bash scripts/install.sh setup-projects-meta
```
Works on Windows under git-bash, Linux, macOS.
## See also
- [`using-projects-meta`](../using-projects-meta/) — runtime policy for
cross-project task aggregation and shared-wiki query / ingest.
- [`setup-context7`](../setup-context7/) — companion pattern for the context7
MCP plugin (similar 8-phase shape).
- Per-project вики/таски живут в mappa (мета в сервисе, решения 14/15) —
setup-скилов `.wiki/`/`.tasks/` больше нет; операции — `using-wiki` /
`using-tasks`.

View File

@@ -1,244 +0,0 @@
---
name: setup-projects-meta
author: ours
version: 1.1.0
description: Installs and configures the local `projects-meta-mcp` stdio server — clones the repo to `~/projects/.common/lib/projects-meta-mcp`, builds it, writes `~/.config/projects-mcp/auth.toml` with the user's Gitea token, clones the shared wiki to `~/projects/.wiki/` (content lives in root), and registers `mcpServers.projects-meta` in `~/.claude.json`. Use this skill when the user says "install projects-meta", "set up projects-meta", "configure projects-meta", "настрой projects-meta", "установи projects-meta", "projects-meta не работает", "projects-meta isn't working", or whenever the `mcp__projects-meta__*` tools are missing in a session that needs cross-project task aggregation or the shared Gitea wiki. Cross-platform — Windows / Linux / macOS. Mutates user-level config and writes secrets; pauses for confirmation before every write.
---
# setup-projects-meta
> One-time skill that gets the local `projects-meta-mcp` server running with the user's Gitea credentials. Stops at confirmation gates because the procedure clones a repo, writes a secret-bearing TOML file, and edits `~/.claude.json`.
Reference: full `projects-meta-mcp` docs live in the shared wiki at `packages/projects-meta-mcp` (fetch via `mcp__projects-meta__knowledge_get` once the server is up).
## When to use
- User explicitly asks: install / set up / configure projects-meta.
- A `using-projects-meta`-driven task fails because `mcp__projects-meta__*` tools aren't available.
- Migrating a stale install (token expired, repo moved, broken cache) — same procedure, Phase 1 detects what's already in place.
- New machine in the user's multi-machine fleet (recall: this is a cross-machine workflow).
## Out of scope
- Issuing or rotating Gitea tokens. This skill *uses* a token the user already has; if there's no token, point them at Gitea's settings page (`https://git.kzntsv.site/user/settings/applications`) and stop until they paste one.
- Running `projects-meta-mcp` itself (the MCP harness spawns it).
- Editing `.tasks/STATUS.md` or wiki content — that's `using-projects-meta` / `using-tasks` / `using-wiki`.
- Any other MCP server.
## Hard rule: don't auto-mutate config
The procedure clones a repo, writes `~/.config/projects-mcp/auth.toml` (carries the Gitea token), and edits `~/.claude.json`. **Always pause for explicit confirmation between Phase 1 (discovery, read-only) and Phase 2 (plan), and again before Phase 3 (backup + writes).** A trigger phrase is permission to run discovery, not permission to clone or write secrets.
## Procedure
### Phase 0 — Environment sanity
- Confirm Claude Code is the current harness (need `mcpServers` registration in `~/.claude.json`).
- Confirm `git`, `node`, `npm` are on `PATH`. Node ≥ 18 (the server uses ES modules).
- Confirm network reachability to `https://git.kzntsv.site` (the Gitea host). On HTTP 401/403 later, the token is dead — stop and ask for a new one.
- Pick paths: `~/projects/.common/lib/projects-meta-mcp`, `~/.config/projects-mcp/`, `~/.cache/projects-mcp/`, `~/projects/.wiki/` (shared wiki clone). POSIX-style `~/...` resolves correctly under git-bash on Windows.
### Phase 1 — Discovery (read-only)
Search, in order. Report only "found at <path>", never echo token values.
**Existing Gitea token.** Look in priority order:
1. `~/.config/projects-mcp/auth.toml` → `gitea_token = "..."`
2. Env var `PROJECTS_META_GITEA_TOKEN`
3. Existing `~/.claude.json` → `mcpServers.projects-meta` block (rare; legacy installs sometimes inline `env.GITEA_TOKEN`)
The first hit wins. Capture internally for Phase 5; **never echo it in chat**.
**Repo install state.** Check whether `~/projects/.common/lib/projects-meta-mcp/.git` exists. If yes, `git -C ~/projects/.common/lib/projects-meta-mcp rev-parse HEAD` → record the SHA so Phase 4 can decide *clone* vs *pull*.
**Build artifact.** Check `~/projects/.common/lib/projects-meta-mcp/dist/server.js`. If absent, Phase 4 will run `npm install && npm run build`.
**Shared wiki clone.** Check if `~/projects/.wiki/.git` exists and `origin` matches `https://git.kzntsv.site/OpeItcLoc03/projects-wiki(.git)?`. If non-matching `origin`, stop and ask — the user may have an unrelated wiki there.
**MCP registration.** Read `~/.claude.json` and check `mcpServers.projects-meta`. Note the command + args. If args point at a stale path, Phase 6 will fix it.
**Cache state.** List `~/.cache/projects-mcp/` (if it exists). Just for the report — don't rely on it.
### Phase 2 — Plan + confirm
Present a single-block plan to the user:
```
Token: <found at <path> | NOT FOUND — will ask>
Repo: <installed at ~/projects/.common/lib/projects-meta-mcp@<sha> | will clone>
Build artifact: <present | will run npm install && npm run build>
Wiki clone: <present at ~/projects/.wiki | will clone | wrong remote — STOP>
MCP entry: <present in ~/.claude.json | will add | will fix path>
Backups: ~/.claude.json.bak-<ts>, ~/.config/projects-mcp/auth.toml.bak-<ts> (if exists)
```
Wait for explicit confirmation ("ok", "go", "поехали"). Anything else → stop.
If no token was found in Phase 1 — first ask: "Paste a Gitea personal access token (scope: `read:repository` for read-only, `write:repository` to enable mutations), or open `https://git.kzntsv.site/user/settings/applications` to create one." Don't proceed past Phase 2 without a token.
### Phase 3 — Backup
Copy each file we will modify to `<file>.bak-YYYYMMDD-HHMMSS`:
```bash
TS=$(date +%Y%m%d-%H%M%S)
[ -f ~/.claude.json ] && cp ~/.claude.json ~/.claude.json.bak-$TS
[ -f ~/.config/projects-mcp/auth.toml ] && cp ~/.config/projects-mcp/auth.toml ~/.config/projects-mcp/auth.toml.bak-$TS
```
Confirm both backups exist (when their source existed) before any further edit. The repo and wiki clones don't need backup — git is the backup.
### Phase 4 — Clone + build
```bash
# Server
if [ -d ~/projects/.common/lib/projects-meta-mcp/.git ]; then
git -C ~/projects/.common/lib/projects-meta-mcp pull --ff-only
else
git clone https://git.kzntsv.site/OpeItcLoc03/projects-meta-mcp ~/projects/.common/lib/projects-meta-mcp
fi
cd ~/projects/.common/lib/projects-meta-mcp
npm install
npm run build
# Shared wiki
mkdir -p ~/projects
if [ -d ~/projects/.wiki/.git ]; then
git -C ~/projects/.wiki pull --ff-only
else
git clone https://git.kzntsv.site/OpeItcLoc03/projects-wiki ~/projects/.wiki
fi
```
Verify `~/projects/.common/lib/projects-meta-mcp/dist/server.js` exists after build. If not — abort, the build failed; ask the user to run `npm run build` manually and paste the output.
### Phase 5 — Write `auth.toml`
```bash
mkdir -p ~/.config/projects-mcp
```
If `~/.config/projects-mcp/auth.toml` already exists and Phase 1 found a valid `gitea_token` line — skip the write. Otherwise, write the file with the token captured in Phase 1 (or freshly pasted in Phase 2):
```toml
gitea_url = "https://git.kzntsv.site"
gitea_user = "OpeItcLoc03" # acting identity (commit author)
gitea_token = "<TOKEN>"
gitea_owners = ["victor", "cancel_music"] # additional Gitea owners to sync
agenda_tasks_repo = "OpeItcLoc03/agenda" # cross-project meta-board (qualified)
# gitea_aggregate_skip_owners = ["OpeItcLoc03"] # opt: sync but hide from `tasks_aggregate`
```
**Schema notes (v2.x server):**
- `gitea_owners` is an array of owners whose repos are scanned by `sync.js` and surfaced in aggregation views. `gitea_user` is acting identity only (commit author footer), not necessarily aggregated.
- `agenda_tasks_repo` is **qualified** (`<owner>/<repo>`). The literal `agenda` in `target_project` resolves through this field.
- `gitea_aggregate_skip_owners` (optional, v2.2.0+) — visited by sync (so mutations work via cache lookup) but hidden from `tasks_aggregate` / `tasks_search`. Useful for keeping infra repos write-able without polluting the dashboard.
- Backwards-compat: legacy installs with only `gitea_user = "X"` and no `gitea_owners` → server reads as `gitea_owners = ["X"]`.
- Legacy `meta_tasks_repo` / `meta_wiki_repo` → renamed to `agenda_tasks_repo` / built-in `projects-wiki`. Old keys ignored on v2.x.
Permissions: on Linux / macOS run `chmod 600 ~/.config/projects-mcp/auth.toml`. On Windows the default ACL is per-user, no extra step.
### Phase 6 — Register in `~/.claude.json`
Edit `~/.claude.json`. Add or update the `mcpServers.projects-meta` block:
```json
{
"mcpServers": {
"projects-meta": {
"command": "node",
"args": ["<ABSOLUTE_PATH_TO>/dist/server.js"]
}
}
}
```
Absolute path resolution:
| Platform | `<ABSOLUTE_PATH_TO>` |
|---|---|
| Windows | `C:/Users/<USER>/projects/.common/lib/projects-meta-mcp` (forward slashes; works in JSON without escaping) |
| Linux | `/home/<USER>/projects/.common/lib/projects-meta-mcp` |
| macOS | `/Users/<USER>/projects/.common/lib/projects-meta-mcp` |
After each edit, validate JSON:
```bash
# Windows (git-bash)
powershell.exe -NoProfile -c "Get-Content '<file>' -Raw | ConvertFrom-Json | Out-Null"
# Linux / macOS
jq empty <file>
# fallback
python -c "import json; json.load(open('<file>'))"
```
If validation fails → restore from `.bak-*` and abort.
### Phase 7 — Smoke test (best-effort) + run initial sync
Best-effort: call `mcp__projects-meta__meta_status`. If it returns a JSON blob with `synced_at` / `wiki_pages_count` — the server is reachable in *this* session.
Then run a one-shot sync to populate the cache:
```bash
cd ~/projects/.common/lib/projects-meta-mcp
node dist/sync.js
```
Expect a non-zero `projects_count` and a fresh `~/.cache/projects-mcp/tasks.json`. On 401 / 403 → token is wrong scope or expired; rotate via `https://git.kzntsv.site/user/settings/applications` and re-edit `auth.toml`.
**Important caveat to relay to the user:** in the *same* session that just ran setup, the MCP server you're talking to is whatever was bound at session start. So a passing `meta_status` only proves "some projects-meta is alive" — not "the registration we just wrote is what's serving it". The real test is after Claude Code restart.
### Phase 8 — Restart guidance + final report
Tell the user:
```
✅ Setup complete. Restart Claude Code so the new mcpServers.projects-meta
registration binds to a fresh stdio session.
After restart:
• mcp__projects-meta__* tools serve from ~/projects/.common/lib/projects-meta-mcp/dist/server.js
• Cache lives at ~/.cache/projects-mcp/tasks.json (refresh: node dist/sync.js)
• Shared wiki clone at ~/projects/.wiki/ — `git -C ~/projects/.wiki pull --ff-only` for fresh anchors
• Backups saved at ~/.claude.json.bak-<ts> (and auth.toml.bak-<ts> if it existed before)
If something breaks after restart:
• Restore from .bak-* and tell me — we'll roll back together.
```
## Rollback procedure
If a problem surfaces (now or after restart):
1. Stop. Don't try to fix forward.
2. Find the most recent `.bak-YYYYMMDD-HHMMSS` next to `~/.claude.json` (and `~/.config/projects-mcp/auth.toml` if applicable).
3. `cp <file>.bak-<ts> <file>` for each.
4. Optional: `rm -rf ~/projects/.common/lib/projects-meta-mcp` and `rm -rf ~/.cache/projects-mcp`. Keep `~/projects/.wiki/` — it's a useful clone regardless of MCP state.
5. Restart Claude Code.
6. Confirm `mcp__projects-meta__*` is gone (or back to the pre-existing version).
7. Report what went wrong so we can fix the procedure.
## Cross-platform notes
The procedure is platform-agnostic. Only auxiliary tooling differs:
| | JSON validate | Backup | Permissions on auth.toml |
|---|---|---|---|
| Windows (git-bash) | `powershell.exe -NoProfile -c "Get-Content '<f>' -Raw \| ConvertFrom-Json \| Out-Null"` | `cp` | per-user ACL by default |
| Linux | `jq empty <f>` (or `python -c "import json; json.load(open('<f>'))"`) | `cp` | `chmod 600` |
| macOS | same as Linux | `cp` | `chmod 600` |
Path forms (`~/.local/...`, `~/.config/...`, `~/projects/...`) are identical on all three.
## Common mistakes
- **Skipping Phase 1.** "User just said 'install projects-meta' — let's go." No — find existing token / repo / wiki first; re-cloning over an existing install loses any local commits in the wiki.
- **Echoing the token.** It's a secret. Edit / Write tool calls inevitably contain it (that's how it gets into `auth.toml`), but no chat output should.
- **Cloning over an unrelated `~/projects/.wiki/`.** If it exists with a different `origin`, stop. The user may have an unrelated wiki there.
- **Writing `auth.toml` with `0644` perms on Linux/macOS.** Token leak. Always `chmod 600` after write.
- **Treating in-session `meta_status` as proof.** Same as the context7 caveat — the active MCP connection was bound at session start.
- **Auto-running on every "use projects-meta".** This skill is intrusive. Trigger only on explicit "install/setup/configure projects-meta", or when MCP tools are missing and the user is blocked.
- **Forgetting `node dist/sync.js`.** Without an initial sync, the cache is empty and `tasks_aggregate` returns nothing — the user thinks setup failed.

View File

@@ -1,137 +0,0 @@
---
name: task-format
author: ours
version: 0.3.0
description: >
Use when creating or editing a task so it is actually claimable and routed —
not silently skipped. Primary channel: **mappa** — create via
`mcp__mappa__task_create` (схема ниже), не руками. Legacy: пока файловый
поллер (agents-task-runner) не переключён на mappa (#984), блоки в
`.tasks/STATUS.md` обязаны совпадать со строгим форматом (шапка, поля
Weight/Notify), иначе поллер молча пропускает. Triggers: «оформить таску для
поллера», «формат таски», «task block format», «make a task the poller will
pick up», «add Weight/Notify», poller / agent-runner not claiming a task.
---
# task-format
Канон создания задачи — **через тул**, не рукописным блоком. Поллер (автономный
раннер) разбирает задачи строгими правилами; формат задаёт, какая таска будет
взята, отмаршрутизирована и зарепорчена, а какая молча пропущена.
> Создаёшь задачу для **другого** проекта/агента? См. `delegate-task` — он ведёт
> через тул + письмо. Работа с бордом (claim/close/status) — `using-tasks`.
## Primary: mappa task.create
Создание задач в mappa (решение 14/15: мета в сервисе) — только через
`mcp__mappa__task_create`, никогда руками вставляй блоки. Тул сам назначает
per-type номер (`t:N`, решение 20) и пишет сущность.
```
mcp__mappa__task_create(
project: <имя проекта>, // обязателен
slug: <kebab-case>, // обязателен, латиница
title: <одна строка>, // опционально
description: <markdown>, // тело; [[refs]] → рёбра (решение 4)
status: ready | active | paused | blocked | done, // по умолчанию ready
claim_token: <токен лиза проекта> // мутация под лизом (решение 19)
)
```
**Мутация под лизом (решение 19):** `task_create` требует `claim_token`
активного лиза проекта (берётся `mcp__mappa__task_claim_next`). Без лиза —
422 busy. (Карв-аут: чтения и инбокс-доставка лиза не требуют.)
**Per-type номер (решение 20):** номер — канонический машинный реф `t:N`
(см. ответы — поле `ref`). Глобальный id — internal, только для addressing
(#1037). Ссылки на задачу в тексте — `[[t:N]]`, не `#<глобальный id>`.
**Slug-правила:** короткий, lowercase, kebab-case, латиница
(`fix-nl-vds-reality-pq-dest`, не `Fix_this_TASK #1`).
## Status emoji ↔ state
| Emoji | State | Значение |
|---|---|---|
| ⚪ | `ready` | единственное состояние, которое поллер берёт |
| 🔴 | `active` | взято / в работе |
| 🟡 | `paused` | возобновляемо |
| 🔵 | `blocked` | ждёт (указать почему в description/where_stopped) |
| 🟢 | `done` | закрыто |
Не путай: 🟢 — это *done*, не «готово».
## Legacy: блок .tasks/STATUS.md (интерм до #984)
Пока файловый поллер (agents-task-runner) не переключён на mappa-лиз (#984),
блоки в `.tasks/STATUS.md`, создаваемые руками/миграцией, обязаны совпадать со
строгим форматом — иначе поллер молча пропускает или паркует. **Это
переходный канон; новые задачи создавай через task_create.**
```markdown
## ⚪ [#1234 my-task-slug] — One-line description.
**Status:** ready
**Created:** 2026-08-23
**Where I stopped:** (not started)
**Next action:** First concrete step the claiming agent runs.
**Branch:** master
**Weight:** needs-claude
**Notify:** OpeItcLoc03/workshop
<!-- created-by: you@machine / from: OpeItcLoc03/workshop / 2026-08-23 -->
---
```
Три load-bearing правила:
1. **Шапка точно:** `## <emoji> [#<n> <slug>] — <description>` — h2, один emoji,
`[#<n> <slug>]` (глобальный номер, без ведущих нулей), разделитель
` — ` (пробел + em-dash + пробел). Несовпавшая шапка = задача не видна вообще.
2. **Поля — строки `**Label:** value`.** Буллеты и проза игнорируются.
3. **`**Created:** yyyy-mm-dd` обязателен** — пишется один раз при создании.
Номера legacy-блоков назначает сервер (`tasks_create` из счётчика
`OpeItcLoc03/agenda/task-counter`) — **никогда не выдумывай номер руками**.
### Поля, которые поллер разбирает
| Field | Format | Meaning |
|---|---|---|
| `**Weight:**` | `cheap-ok` \| `needs-claude` \| `needs-human` | Тир маршрутизации. **Обязателен** для авто-взятия. |
| `**Notify:**` | `<owner>/<repo>` | Инбокс-адрес для событий close/park/delivery-failure. |
| `**Requirements:**` | CSV (`needs-db, needs-secrets`) | Capability-гейт: агент должен держать ВСЕ. |
| `**Runtime allowed:**` | CSV (`claude-opus`) | Runtime-whitelist. |
| `**Consult policy:**` | `auto` \| `human-only` \| `strict-human` | Эскалация consult; default `human-only`. |
| `**Blocker:**` | CSV blocker-slug'ов | Только на 🔵; авто-unblock при 🟢 всех. |
| `**Next action:** / **Where I stopped:** / **Branch:**` | free text | Резюмируемость. |
`**Owner:** / **Claim token:** / **Claim expires at:**` — claim-штамп, пишет и
чистит поллер. Не автори руками; залипший штамп на ⚪ блокирует поллер.
**Weight — поле, решающее взятие:** без `**Weight:**` поллер берёт задачу, не
находит тир и паркует в 🔵 (`no backend for weight_tier: unknown`). Обычный код
→ `needs-claude`; критикал-инфра (поллер, MCP-серверы, деплой, CI, git-хуки) →
`needs-human` (никогда не авто).
## Common mistakes
| Mistake | Fix |
|---|---|
| Рукописный блок вместо `task_create` | Создавай через тул — номер/формат серверные. |
| `### Title` / буллеты вместо полей | `## <emoji> [#n slug] — desc` + `**Field:** value`. |
| 🟢 для ready | 🟢 — done. Ready — ⚪. |
| Шапка `[slug]` без номера | `[#n slug]` — номер машинный ключ. |
| Выдуманный номер | Номер — только от сервера (task_create). |
| `**Created:**` отсутствует (legacy) | Добавить — обязательное поле. |
| Ссылка `#<глобальный id>` | Ссылайся `[[t:N]]` (решение 20/#1037). |
| Без `**Weight:**` (legacy) | Ставь всегда, или задача паркуется. |
| Дефис/двоеточие вместо ` — ` в шапке | Разделитель — пробел + em-dash + пробел. |
## Verify
Задача корректна, когда: создана через `task_create` (или legacy-блок: шапка
`## <emoji> [#n slug] — …`, emoji = `**Status:**`, `**Created:**` есть, поля —
`**Label:**` строки, есть `**Weight:**` и `**Notify:**`); slug kebab-case;
ссылки на неё — `[[t:N]]`.

View File

@@ -1,118 +0,0 @@
---
name: task-loop
author: ours
version: 0.1.0
description: >
Use when the user asks you to work the task board yourself, in this
session, one task after another — «поработай очередь», «прогони доску»,
«бери задачи по очереди», «работай пока не скажу стоп», «work the queue»,
«drain the board», «keep working tasks until I say stop». Does NOT apply
to delegating work to another agent/project (→ delegate-task), to one
named task you already know (→ using-tasks), or to configuring the
background poller.
---
# task-loop
Work the board **in this session**: claim the next ready task, do it, close it, claim the next — until the queue is empty or the user says stop.
**Core principle:** an interactive loop, not a daemon. You stay in the chair. Empty queue → **stop and report**, never spin a wait-timer. No subprocess, no `CronCreate` (that schedules a *separate* session — exactly the daemon you're replacing), no short `ScheduleWakeup` poll — those are the unattended poller's job, not yours here.
**REQUIRED SUB-SKILL:** `using-tasks` owns the board, the `.tasks/.lock` session lock, the `session_break` gate, and the pre-close coverage check. This skill drives the loop *through* those rules — it does not replace them.
**REQUIRED SUB-SKILL:** `project-discipline` — commit/push gate (Rule 4) and sensitive-artifact handling apply to every task you touch.
## When to use
**Activates:** «поработай очередь», «прогони доску», «бери задачи по очереди», «работай пока не скажу стоп», «work the queue», «drain the board», «keep working tasks until I say stop».
**Does NOT apply:**
- Delegating work to another agent/project → `delegate-task`.
- One specific task you already named → `using-tasks` (switch/resume that task).
- Setting up / debugging the background poller or agent-runner → that is infra, not this loop.
## The loop
Run this cycle. One task at a time.
```dot
digraph task_loop {
rankdir=TB;
claim [shape=box, label="tasks_claim_next\n(current project, confirm=true)"];
empty [shape=diamond,label="task returned?"];
stop [shape=box, label="STOP — report board drained"];
work [shape=box, label="do the work this session"];
done [shape=diamond,label="completed?"];
park [shape=box, label="park: blocked (external) | paused (resumable)"];
gate [shape=diamond,label="consult_policy = human-only/strict-human?"];
consult [shape=box, label="STOP before close/commit — consult user"];
close [shape=box, label="pre-close coverage check → tasks_close"];
brk [shape=diamond,label="session_break marker on closed task?"];
boundary[shape=box, label="STOP — print SESSION BOUNDARY"];
claim -> empty;
empty -> stop [label="no ready tasks"];
empty -> work [label="yes"];
work -> done;
done -> park [label="no"];
done -> gate [label="yes"];
gate -> consult [label="yes"];
gate -> close [label="auto"];
close -> brk;
brk -> boundary [label="yes"];
brk -> claim [label="no"];
park -> claim;
}
```
1. **Claim** the next ready task with `tasks_claim_next(claimer_identity, filter, confirm=true)`.
- `claimer_identity` = `<machine>:<runtime>:<session>` (e.g. `DESKTOP-NSEF0UK:claude-opus:<session>`).
- `filter.project` = **the current project** (qualified `<owner>/<repo>`) by default. Only widen to other projects when the user explicitly asks ("прогони все доски" / passes a project list).
- The server already excludes `weight: needs-human` and anti-self-review tasks — you will never claim those.
2. **No task returned** → the queue is drained. **STOP** and report (see *Empty queue*). Do not poll.
3. **Do the work this session.** All your tools are available. Read the task description and per-task `<slug>.md`. Set the task `active` if it isn't already.
4. **Honor the gate before the irreversible step.** Use the `consult_policy` returned by the claim:
- `auto` → full autopilot through close.
- `human-only` / `strict-human` → do the work, then **STOP before `tasks_close` / commit** and consult the user. Don't barrel through.
- **Push is never automatic** regardless of policy — `project-discipline` Rule 4 (commit freely, push only on an explicit per-session grant).
5. **Close** with the `using-tasks` pre-close coverage check, then `tasks_close(target_project, slug, confirm=true, note=…)`.
6. **session_break gate.** After the close, **before claiming the next task**, honor the `using-tasks` `session_break` check: if the closed task carries the marker → print the `🔚 SESSION BOUNDARY` line and **STOP** (do not claim next). Otherwise → back to step 1.
## When a task can't be finished
Never leave a claimed task hanging (its claim expires in 10 min and it returns as a zombie), and never `tasks_close` unfinished work (that lies to the board).
- **External / unresolvable blocker** discovered mid-task (missing upstream, needs a human decision, scope change) → `tasks_update(slug, status="blocked", blocker="<concrete fact + what's needed>")`. Roll back partial work that would break the build. Then continue the loop (the blocker is isolated; the next claim won't return this task).
- **Interrupted or resumable by you** (you ran out of budget, the user stops you mid-task) → `tasks_update(slug, status="paused", where_stopped=…, next_action=…)`.
A single failing task does not stop the loop — park it and move to the next.
## Empty queue & stopping
The loop ends on the **first** of:
- **Empty queue** — `tasks_claim_next` returns no ready task → stop, report what you closed/parked, and wait for the user. Do **not** `ScheduleWakeup`, `CronCreate`, or sleep-poll for new tasks.
- **Explicit user signal** — «стоп», «хватит», «отбой». Park any in-flight claimed task (paused) before stopping.
- **Budget** — `budget.remaining()` near zero → park the current task (paused) and report.
**Long-running watch (opt-in only).** If the user explicitly says «работай пока не скажу стоп» *and* wants you to keep checking for newly-arrived tasks, use **`ScheduleWakeup`** — it re-invokes *this* session — with a **long** interval (≥1200 s). **Never `CronCreate`** even here: it starts a *separate* scheduled session, i.e. the daemon this skill exists to avoid. And never a short poll. Default is still stop-on-empty; only arm a wakeup on an explicit standing request.
## Heartbeat
A claim lives 10 minutes. If a single task will take longer than ~8 minutes, call `tasks_heartbeat(slug, claim_token)` periodically to keep the claim alive. Short tasks need no heartbeat. (The in-session `.tasks/.lock` is a separate 2-hour lock owned by `using-tasks` session start/end — don't manage it from the loop.)
## What NOT to do
- **No daemon, no `CronCreate`, no spawned claude, no subprocess** to "run the queue" — `CronCreate` starts a separate scheduled session; the whole point is you do it in *this* session.
- **No busy-poll on empty** — empty queue is a natural stop, not a wait-loop. A short `ScheduleWakeup` loop burns tokens for nothing. The only exception is the explicit long-watch opt-in above (a single ≥1200 s `ScheduleWakeup`, never `CronCreate`).
- **Don't widen scope silently** — default to the current project; claim other boards only when the user asks.
- **Don't `tasks_close` unfinished work** and **don't leave a task claimed** when blocked — park it (blocked/paused).
- **Don't skip the `session_break` gate** between tasks — a milestone/domain-switch marker means stop, even if more tasks are ready.
- **Don't autopilot through a `human-only`/`strict-human` task's close/commit**, and **never auto-push** — consult first.
- **Don't blind-retry** a task that failed for an external reason — diagnose once, record the blocker, move on.
## Red flags — STOP
- "I'll set a timer to check for new tasks" → no. Stop on empty; report.
- "I'll spawn a background worker to drain faster" → no. One task at a time, this session.
- "User said work-until-stop, I'll `CronCreate` a recurring run" → no. `CronCreate` is a separate scheduled session = the daemon. Long-watch uses a single long `ScheduleWakeup` on *this* session.
- "It's sensitive but consult_policy says auto, I'll just commit" → push still needs a grant; sensitive close still respects the gate.
- "The task isn't done but I'll close it and note it" → never close unfinished. Park it.

View File

@@ -85,11 +85,10 @@ setup; pi loads `~/.agents/skills` by default. Verify with `pi --help` / a fresh
The update scripts (`scripts/update.sh` and `scripts/update.ps1`) handle: The update scripts (`scripts/update.sh` and `scripts/update.ps1`) handle:
1. **git pull --ff-only** in `~/projects/skills/` (stash if dirty, pop after). 1. **git pull --ff-only** in `~/projects/skills/` (stash if dirty, pop after).
2. **Conditionally rebuild projects-meta-mcp** — if `~/projects/.common/lib/projects-meta-mcp/` has a `.git` directory and source changed (`git pull` fetched new commits), run `npm run build`. 2. **Conditionally rebuild interns-mcp** — same pattern, `pip install -e .`.
3. **Conditionally rebuild interns-mcp** — same pattern, `pip install -e .`. 3. **Install all skills** via `install.sh` / `install.ps1`.
4. **Install all skills** via `install.sh` / `install.ps1`. 4. **Show version diff** — before/after `version:` frontmatter for each skill.
5. **Show version diff** — before/after `version:` frontmatter for each skill. 5. **Print reload hints** — `/reload-mcp` if MCP changed, new session otherwise.
6. **Print reload hints** — `/reload-mcp` if MCP changed, new session otherwise.
## Out of scope ## Out of scope

View File

@@ -1,7 +1,7 @@
--- ---
name: using-markitdown name: using-markitdown
author: ours author: ours
version: 1.0.1 version: 1.1.0
description: Use when capturing external content into a markdown-based knowledge base, wiki `raw/` directory, or any pipeline that must preserve the source's full text — for web pages, PDFs, DOCX/PPTX/XLSX, EPUB, CSV/JSON/XML, ZIP archives, images (with OCR/EXIF), audio (with transcription), or YouTube URLs. Also use when WebFetch returned an LLM-summarized version but the raw content is what's needed. description: Use when capturing external content into a markdown-based knowledge base, wiki `raw/` directory, or any pipeline that must preserve the source's full text — for web pages, PDFs, DOCX/PPTX/XLSX, EPUB, CSV/JSON/XML, ZIP archives, images (with OCR/EXIF), audio (with transcription), or YouTube URLs. Also use when WebFetch returned an LLM-summarized version but the raw content is what's needed.
--- ---
@@ -52,7 +52,7 @@ No mount caveats: the CLI is a normal local process. The old Docker `-v` mount t
1. markitdown "https://example.com/foo.pdf" -o .wiki/raw/<slug>.md (kebab-case, Latin only) 1. markitdown "https://example.com/foo.pdf" -o .wiki/raw/<slug>.md (kebab-case, Latin only)
2. Inspect the head of the result. If it looks like a sign-in/cookie/consent page, abort — ask the user for an alternative (manual save, paste, authenticated source). 2. Inspect the head of the result. If it looks like a sign-in/cookie/consent page, abort — ask the user for an alternative (manual save, paste, authenticated source).
3. Register the new file in .wiki/raw/README.md. 3. Register the new file in .wiki/raw/README.md.
4. Hand off to the wiki ingest workflow (creates sources/<slug>.md summary + entity/concept updates). 4. Hand off to the wiki ingest workflow (creates summaries/<slug>.md summary + entity/concept updates).
``` ```
For a huge (book-length) document, write straight to a file with `-o` and summarize *from the saved file* — do not pipe the whole markdown through working context. For a huge (book-length) document, write straight to a file with `-o` and summarize *from the saved file* — do not pipe the whole markdown through working context.
@@ -63,7 +63,7 @@ For a huge (book-length) document, write straight to a file with `-o` and summar
|---|---|---| |---|---|---|
| Output is a Google/Microsoft sign-in page in some random language | URI behind auth wall | Ask user to export the content manually (Save as PDF, copy-paste) and put it in `raw/` | | Output is a Google/Microsoft sign-in page in some random language | URI behind auth wall | Ask user to export the content manually (Save as PDF, copy-paste) and put it in `raw/` |
| Output is mostly nav/cookie banner text | Site is JS-rendered or anti-bot | Try the cached or print URL; or ask user for HTML export | | Output is mostly nav/cookie banner text | Site is JS-rendered or anti-bot | Try the cached or print URL; or ask user for HTML export |
| Output lacks images / diagrams | Markdown is text-only by design | Save the original asset separately under `raw/assets/`; reference it from the `sources/` summary | | Output lacks images / diagrams | Markdown is text-only by design | Save the original asset separately under `raw/assets/`; reference it from the `summaries/` summary |
| `markitdown: command not found` | CLI not on `PATH` | Confirm with `markitdown --version` (expect `markitdown 0.1.6`); install with `pip install markitdown[all]` if missing | | `markitdown: command not found` | CLI not on `PATH` | Confirm with `markitdown --version` (expect `markitdown 0.1.6`); install with `pip install markitdown[all]` if missing |
| Huge output (book-length) | Whole document converted in one call | Use `-o <file>` to save raw, then summarize *from the saved file* — do not hold the entire markdown in working context | | Huge output (book-length) | Whole document converted in one call | Use `-o <file>` to save raw, then summarize *from the saved file* — do not hold the entire markdown in working context |

View File

@@ -1,170 +0,0 @@
# using-projects-meta
Runtime policy for the local `projects-meta-mcp` stdio server. Two
responsibilities, one server:
1. **Cross-project task aggregation** — reads / writes `.tasks/STATUS.md` in
any of the user's Gitea repos.
2. **Shared knowledge wiki** — query / ingest a single Gitea-backed wiki at
`~/projects/projects-wiki/.wiki/` (clone root: `~/projects/projects-wiki/`,
Gitea repo: `projects-wiki`).
`using-projects-meta` governs *usage* of an installed server. Initial setup
(clone, build, `auth.toml`, MCP registration) is owned by
[`setup-projects-meta`](../setup-projects-meta/).
Full server reference:
`mcp__projects-meta__knowledge_get slug=packages/projects-meta-mcp`.
## When it triggers
- User asks for cross-project state ("what's on the boards", "across all
projects", "что у меня на досках", "по всем проектам").
- User wants to query / ingest the shared wiki ("check shared wiki", "search
projects-wiki", "ingest into shared wiki", "общая вики", "заингесть в общую").
- User wants to create / update / close a task in *another* project from the
current cwd ("заведи в проекте X задачу", "close task Y in project Z").
- User asks for sync diagnostics ("when did the cache last refresh", "are there
sync errors").
- If `mcp__projects-meta__*` tools are missing, this skill delegates to
[`setup-projects-meta`](../setup-projects-meta/) before doing anything else.
## Local-first rule (critical)
For the **current** project — read disk directly (`.tasks/STATUS.md`,
`.wiki/index.md`). The MCP cache:
- May be stale (sync runs only when triggered).
- Hides `🟢 done` by default.
- May not contain unpushed projects.
Use MCP only for **other** projects, **other** machines, or the **shared**
wiki content. See the table below.
| Question | Where to read |
|---|---|
| "What's the status of *this* project?" | local `.tasks/STATUS.md` |
| "What's on all my boards?" | `mcp__projects-meta__tasks_aggregate` |
| "Has *this* project's wiki got X?" | local `.wiki/index.md` |
| "Has the **shared** wiki got X?" | `mcp__projects-meta__knowledge_search` |
| "Sync state across machines?" | `mcp__projects-meta__meta_status` |
## Step 0 — Freshness gate (v1.1.0, mandatory pre-flight)
`projects-meta` is a bus between machines — another host may have pushed
minutes ago. Without this gate, reads return stale data and writes hit
sha-based optimistic-lock 422s with no explanation.
Before **any** `tasks_*` or `knowledge_*` call:
1. `mcp__projects-meta__meta_status` — probe cache age + errors.
2. If `cache_age_minutes` > 10 OR `errors_count` > 0 →
`node ~/projects/.common/lib/projects-meta-mcp/dist/sync.js`.
3. For shared-wiki **writes** (`knowledge_ingest`, `knowledge_promote`) →
**also** `git -C ~/projects/projects-wiki pull --ff-only`. Unconditional.
The MCP server uses sha-based optimistic locking on the wiki repo;
without an up-to-date local SHA the commit is rejected with a 422.
4. For tasks-mutations (`tasks_create`/`update`/`close`) → sync via
`dist/sync.js` is enough; there's no local clone of the target tasks repo.
5. If sync returns **401 / 403** → STOP. Token is dead. Send the user to
`~/.config/projects-mcp/auth.toml` to rotate `gitea_token`. Don't
pretend success, don't retry silently.
**Don't sync unconditionally** on every call — overhead + 401-risk for
casual reads. The 10-minute window is the chosen threshold.
**Don't apply Step 0 to `meta_status` itself** — it's the probe.
## Two operation classes
### Read (no confirmation)
`tasks_aggregate`, `tasks_search`, `tasks_get`, `knowledge_search`,
`knowledge_get`, `knowledge_suggest_promote`, `meta_status` — all
side-effect-free. Call directly, cite the result.
### Mutate (always two-step)
`tasks_create`, `tasks_update`, `tasks_close`, `knowledge_ingest`,
`knowledge_promote` — write to Gitea. Procedure:
1. Call **without** `confirm: true` → returns dry-run preview (proposed file
diff + commit message).
2. Show the preview to the user. Wait for explicit "ok" / "go" / "поехали".
3. Re-call with `confirm: true` → committed.
**Never inline `confirm: true` on the first call.** A trigger phrase is
permission to plan, not to commit.
## Tool quick reference
### Read
| Tool | Required args | Purpose |
|---|---|---|
| `mcp__projects-meta__tasks_aggregate` | — | All active tasks across cached projects |
| `mcp__projects-meta__tasks_search` | `query` | Substring search across slug + next_action |
| `mcp__projects-meta__tasks_get` | `project` | Raw STATUS.md of one project (cache snapshot) |
| `mcp__projects-meta__knowledge_search` | `query`; opt `domain`, `limit` | Shared-wiki search; default domain auto-detected from cwd |
| `mcp__projects-meta__knowledge_get` | `slug` | Full text of one wiki page |
| `mcp__projects-meta__knowledge_suggest_promote` | — | Local `.wiki/concepts/` candidates for shared promotion |
| `mcp__projects-meta__meta_status` | — | Sync diagnostics (cache age, project / page / error counts) |
### Mutate (need `write:repository` Gitea scope)
| Tool | Required args | Effect |
|---|---|---|
| `mcp__projects-meta__tasks_create` | `target_project`, `slug`, `description`, `next_action` | Append block to target's `.tasks/STATUS.md` via Gitea commit |
| `mcp__projects-meta__tasks_update` | `target_project`, `slug` + ≥1 mutable field | Sha-based optimistic lock; 422 on conflict |
| `mcp__projects-meta__tasks_close` | `target_project`, `slug` (+ opt `note`) | Marks task 🟢 done with identity-footer |
| `mcp__projects-meta__knowledge_ingest` | `target_project`, `type`, `slug`, `body` | Three commits: `<type>/<slug>.md` + `index.md` + `log.md` |
| `mcp__projects-meta__knowledge_promote` | `target_project`, `slug`, `body` | Move `raw/<slug>.md` → `sources/<slug>.md` |
`type` ∈ `entities` / `concepts` / `packages` / `sources` / `raw`.
`target_project` = Gitea repo name, or `_meta` (meta-tasks / meta-wiki repos
from `auth.toml`).
## Common mistakes
- **Reading current project's tasks via `tasks_get`.** Read `.tasks/STATUS.md`
on disk; the MCP cache is for *other* projects.
- **Inlining `confirm: true` on first call.** Always preview first; show user;
only then `confirm: true`.
- **Confusing the local `.wiki/` with the shared `projects-wiki`.** They are
two different stores. `using-wiki` operates on the local one;
`using-projects-meta` queries / ingests the shared one.
- **Acting on stale `tasks_aggregate`.** If `meta_status.age_seconds` > 3600,
either run `node dist/sync.js` (in `~/projects/.common/lib/projects-meta-mcp`) or warn the
user about staleness.
- **Vague `knowledge_search` queries.** "auth" returns noise. Multi-word,
specific queries return targeted snippets.
- **Wrong `type` on `knowledge_ingest`.** Mis-typed pages land in the wrong
section and break `index.md`. Pick from the five canonical types.
## When NOT to use
- The current project's own tasks — read `.tasks/STATUS.md`.
- The current project's own wiki — read `.wiki/`.
- Library / framework documentation — that's [`using-context7`](../using-context7/).
- Repo-internal code search — that's `Glob` / `Grep`.
- One-off git history questions — `git log`.
## Install
From the repo root:
```bash
bash scripts/install.sh using-projects-meta
```
Works on Windows under git-bash, Linux, macOS.
## See also
- [`setup-projects-meta`](../setup-projects-meta/) — companion, owns server
install + MCP registration.
- [`using-context7`](../using-context7/) — sister skill for library docs (same
using-X structure).
- [`using-tasks`](../using-tasks/), [`using-wiki`](../using-wiki/) —
per-project policies for in-repo `.tasks/` and `.wiki/`. Orthogonal to this
skill; together they cover both per-project and cross-project state.

View File

@@ -1,238 +0,0 @@
---
name: using-projects-meta
author: ours
version: 1.2.0
description: Use when working across multiple projects on one or many machines — cross-project task aggregation (`mcp__projects-meta__tasks_*`), shared Gitea-backed wiki query / ingest (`mcp__projects-meta__knowledge_*`), or sync diagnostics (`mcp__projects-meta__meta_status`). Triggers on phrases like "across all projects", "what's on the boards", "check shared wiki", "search projects-wiki", "ingest into shared wiki", "что у меня на досках", "по всем проектам", "общая вики", "cross-project status", or any time the user wants to see / mutate state in another repo than the current cwd. v1.1.0 mandates a Step 0 freshness gate (probe `meta_status`, sync if stale, pull `projects-wiki` before shared-wiki writes) — see SKILL body. Mutation tools require two-step preview → confirm. Skip for the **current** project's tasks/wiki — those live on disk in `.tasks/` / `.wiki/`.
---
# Using the projects-meta MCP server
## Overview
`projects-meta-mcp` is a local stdio MCP server. Two responsibilities:
1. **Cross-project task aggregation** — parses `.tasks/STATUS.md` from every repo on the user's Gitea, caches them in `~/.cache/projects-mcp/tasks.json`. Read tools (`tasks_aggregate`, `tasks_search`, `tasks_get`) hit the cache. Mutations (`tasks_create`, `tasks_update`, `tasks_close`) commit back to Gitea with sha-based optimistic lock.
2. **Shared knowledge wiki** — single Gitea repo (`projects-wiki`) cloned at `~/projects/projects-wiki/` with content at `~/projects/projects-wiki/.wiki/`, structured as packages / concepts / entities / sources / raw. `knowledge_search` + `knowledge_get` for queries, `knowledge_ingest` + `knowledge_promote` for writes.
Source of truth: Gitea (`https://git.kzntsv.site`, owner `OpeItcLoc03`). Cache and clone are local convenience.
Full reference: `mcp__projects-meta__knowledge_get slug=packages/projects-meta-mcp`.
## Prerequisites
This skill assumes `mcp__projects-meta__*` tools are available. If they aren't (tools missing from the session, or calls fail with a connection error), the server isn't running for this session. Trigger the **`setup-projects-meta`** skill to clone, build, write `auth.toml`, and register `mcpServers.projects-meta` in `~/.claude.json`. It's a one-time procedure with confirmation gates.
## Local-first rule
**For the current project — read disk directly.** `.tasks/STATUS.md` and `.wiki/` files in cwd are always fresher than the MCP cache. The cache:
- May be stale (default sync runs only when triggered).
- Hides 🟢 done by default.
- May not contain locally-developed projects that aren't pushed to Gitea yet.
Use MCP only for **other** projects, **other** machines, or **shared** wiki content.
| Question | Where to read |
|---|---|
| "What's the status of *this* project?" | local `.tasks/STATUS.md` |
| "What's on all my boards?" | `mcp__projects-meta__tasks_aggregate` |
| "Has *this* project's wiki got a page on X?" | local `.wiki/index.md` + relevant file |
| "Has the **shared** wiki got a page on X?" | `mcp__projects-meta__knowledge_search` |
| "Sync state across machines?" | `mcp__projects-meta__meta_status` |
## When to use
- Cross-project task overview ("what am I working on across projects", "по всем проектам", "across the board").
- Hopping into another repo's task state without cloning it ("what's the status of project X").
- Querying the shared wiki for cross-cutting concepts (patterns, package references, design notes that apply to several repos).
- Ingesting a finished design / decision into the shared wiki so other machines / projects can see it.
- Creating a task in another project's `.tasks/STATUS.md` from the current repo (cross-project handoff).
- Sync diagnostics (when did the cache last refresh, are there errors, how many projects).
## When NOT to use
- The current project's own tasks or wiki — read disk.
- Anything inside a single project — `.tasks/<task>.md` and `.wiki/<page>.md` are always closer.
- One-off questions answered by `git log` or a single file.
- Library / framework documentation — that's `using-context7`.
- Code search — that's `Glob` / `Grep`.
## Step 0 — Freshness gate (run before any tool)
`projects-meta` is a bus between machines. Another host may have pushed minutes ago. Without this gate, reads return stale data and writes hit sha-based optimistic-lock 422s with no explanation. Mandatory pre-flight, every session, every workflow:
```
1. Call mcp__projects-meta__meta_status.
2. Branch on cache freshness:
• If cache_age_minutes > 10 OR errors_count > 0:
run `node ~/projects/.common/lib/projects-meta-mcp/dist/sync.js`
(or `npm run sync` from ~/projects/.common/lib/projects-meta-mcp).
• Else: cache is fresh enough — skip sync, no need to hit the network.
3. For shared-wiki WRITES (knowledge_ingest, knowledge_promote):
ALWAYS additionally run `git -C ~/projects/projects-wiki pull --ff-only`
regardless of cache age. The MCP server uses sha-based optimistic locking;
without an up-to-date local file SHA, the commit will be rejected (422)
and the failure mode is opaque to the user.
4. For tasks-mutations (tasks_create, tasks_update, tasks_close):
sync via dist/sync.js is enough — there's no local clone of the target
tasks repo, mutations go straight through Gitea API. Sync only refreshes
the local view so you reason from current state.
5. If sync returns 401 or 403:
STOP. The Gitea token in ~/.config/projects-mcp/auth.toml is dead or
wrong-scoped. Tell the user explicitly:
"Gitea sync failed with <401|403>. Rotate gitea_token in
~/.config/projects-mcp/auth.toml (Gitea: settings/applications)
and rerun."
Do not pretend sync succeeded. Do not retry silently.
```
**Don't sync unconditionally on every call.** Network overhead + risk of 401 even on a casual "what's on my boards". The 10-minute cache window is the right balance — catches multi-machine drift without burning Gitea round-trips for back-to-back questions.
**Don't apply Step 0 to `meta_status` itself** — it's the freshness probe, not a downstream read.
## Workflow
### Read (no confirmation needed)
```
0. Run Step 0 — Freshness gate (above) first.
1. Identify what you need: cross-project tasks? shared wiki page? sync state?
2. Pick the right read tool (table below).
3. Cite the result with the source slug / project name.
```
### Mutate (always two-step)
```
0. Run Step 0 — Freshness gate (above) first.
For shared-wiki writes (knowledge_ingest, knowledge_promote): unconditional
`git -C ~/projects/projects-wiki pull --ff-only` is part of Step 0.
1. Identify the mutation: tasks_create / tasks_update / tasks_close / knowledge_ingest / knowledge_promote.
2. Call the tool WITHOUT `confirm: true` → returns a dry-run preview (the proposed file diff and the Gitea commit message).
3. Show the preview to the user. Wait for explicit "ok" / "go" / "поехали".
4. Re-call with `confirm: true` to commit.
```
**Never inline `confirm: true` on the first call.** A trigger phrase ("create a task in project X") is permission to *plan*, not to *commit*.
## Tool quick reference
### Read tools
| Tool | Required args | Purpose |
|---|---|---|
| `mcp__projects-meta__tasks_aggregate` | — | All active tasks across all cached projects |
| `mcp__projects-meta__tasks_search` | `query` | Substring search across slug + next_action |
| `mcp__projects-meta__tasks_get` | `project` | Raw STATUS.md of one project (cached snapshot) |
| `mcp__projects-meta__knowledge_search` | `query`; opt `domain`, `limit` | Shared-wiki search; auto-detects domain from cwd, pass `domain="all"` to disable |
| `mcp__projects-meta__knowledge_get` | `slug` | Full text of one wiki page (e.g. `packages/projects-meta-mcp`) |
| `mcp__projects-meta__knowledge_suggest_promote` | — | Local `.wiki/concepts/` candidates for shared-wiki promotion |
| `mcp__projects-meta__meta_status` | — | Sync diagnostics: cache age, project count, error count, page count |
### Mutation tools (need `write:repository` Gitea scope; preview → confirm)
| Tool | Required args | Effect |
|---|---|---|
| `mcp__projects-meta__tasks_create` | `target_project`, `slug`, `description`, `next_action` (+ opt `where_stopped`, `status`, `blocker`, `branch`, `source_project`) | Append block to `<target>/.tasks/STATUS.md` via Gitea commit |
| `mcp__projects-meta__tasks_update` | `target_project`, `slug` + ≥1 of `where_stopped` / `next_action` / `blocker` / `branch` / `description` / `status` | Sha-based optimistic lock; 422 on conflict |
| `mcp__projects-meta__tasks_close` | `target_project`, `slug` (+ opt `note`) | Sets task to 🟢 done; appends identity-footer |
| `mcp__projects-meta__knowledge_ingest` | `target_project`, `type`, `slug`, `body` (+ opt `frontmatter`, `source_project`) | Three commits: `<type>/<slug>.md` + `index.md` + `log.md`. `type` ∈ entities / concepts / packages / sources / raw |
| `mcp__projects-meta__knowledge_promote` | `target_project`, `slug`, `body` (+ opt `frontmatter`, `source_project`) | Move `raw/<slug>.md` → `sources/<slug>.md` with auto `raw_path` link |
`target_project` is **qualified** `<owner>/<repo>` (e.g. `victor/books`, `OpeItcLoc03/skills`), or the literal `agenda` for the cross-project meta-board (resolves via `agenda_tasks_repo` in `auth.toml`). Bare names (`books`) are rejected with a hint to use the qualified form. Cross-cutting design: shared wiki → `concepts/projects-meta-multi-owner`.
## Examples
### Read example: cross-project status
User: "что у меня на досках?"
```
1. mcp__projects-meta__tasks_aggregate
→ 7 projects, 12 active tasks
2. Group by project, summarize 1 line per active task.
Cite project name; if a task is stale (cache age > 1h), flag it.
```
### Read example: shared wiki query
User: "есть ли в общей вики что-то про setup-using паттерн?"
```
1. mcp__projects-meta__knowledge_search
query: "setup-using skill pair pattern"
domain: "all"
→ hits include concepts/setup-using-skill-pair
2. mcp__projects-meta__knowledge_get
slug: "concepts/setup-using-skill-pair"
→ full text
3. Summarize, link with markdown to the slug.
```
### Mutation example: create cross-project task
User: "заведи в проекте books задачу на миграцию `settings.json`"
```
1. mcp__projects-meta__tasks_create
target_project: "victor/books"
slug: "settings-json-migration"
description: "<...>"
next_action: "<...>"
(no `confirm`)
→ preview: proposed STATUS.md diff + commit message
2. Show preview to user.
3. User: "ok, go"
4. mcp__projects-meta__tasks_create
(same args + confirm: true)
→ committed to Gitea
```
### Mutation example: closing a cross-project task
User: "close `[projects-meta-skills]` in skills"
```
1. mcp__projects-meta__tasks_close
target_project: "OpeItcLoc03/skills"
slug: "projects-meta-skills"
note: "<one-line summary>"
(no `confirm`)
→ preview
2. User confirms.
3. Re-call with confirm: true.
```
## Common mistakes
| Mistake | Fix |
|---|---|
| Reading current project's tasks via `tasks_get` instead of disk | Read `.tasks/STATUS.md` directly. MCP is for *other* projects. |
| Inlining `confirm: true` on the first mutation call | Always preview first; show user; only then `confirm: true`. |
| Using `knowledge_search` for the project's own wiki | The shared wiki is a separate Gitea repo. Local `.wiki/` is in cwd. |
| Acting on a stale `tasks_aggregate` without checking `meta_status` | Step 0 — Freshness gate is mandatory. If `cache_age_minutes` > 10 (or errors > 0), run `node ~/projects/.common/lib/projects-meta-mcp/dist/sync.js` first. |
| Skipping `git -C ~/projects/projects-wiki pull` before `knowledge_ingest` / `knowledge_promote` | sha-based optimistic lock will reject the commit (422) and the failure is opaque. Pull is unconditional for shared-wiki writes — fast-forward is a no-op when current. |
| Treating sync 401/403 as "MCP is fine, the page just doesn't exist yet" | 401/403 means the Gitea token is dead. Stop, tell the user to rotate `gitea_token` in `~/.config/projects-mcp/auth.toml`. Never guess on stale data. |
| Calling `knowledge_ingest` with the wrong `type` | `type` must be one of `entities` / `concepts` / `packages` / `sources` / `raw`. Mis-typed pages land in the wrong section and break `index.md`. |
| Vague `knowledge_search` queries ("auth", "config") | Specific multi-word queries return targeted snippets; vague ones return noise. |
| Forgetting `domain="all"` when searching across families | Default `domain` is auto-detected from cwd; use `"all"` if the wiki page lives in a different family. |
| Passing bare project name (`target_project: "books"`) to mutation tools | v2.x rejects bare names. Use qualified `<owner>/<repo>` (e.g. `victor/books`, `OpeItcLoc03/skills`). Literal `agenda` is the only exception (cross-project meta-board). |
## Red flags
- "I'll just commit it directly" → no. Mutation tools have a preview step for a reason — silent writes to another repo are a recipe for drift.
- "The cache is fresh enough" → run Step 0. The 10-minute window is the threshold; below it skip sync, above it sync. Don't eyeball this — the bus moves fast in cross-machine sessions.
- "I'll skip the pull, my last write was 30 seconds ago" → another machine pushed in between. Always pull before shared-wiki writes; the sha-lock check is your only safety net.
- "I'll skip the wiki page" → if you're answering a cross-cutting question and there's no wiki page, that's a `knowledge_ingest` candidate. Surface it to the user.

View File

@@ -1,87 +0,0 @@
---
name: using-system-snapshot
author: ours
version: 1.0.0
description: "Use at the start of an ops-context session, and ALWAYS before asserting anything about the mappa meta-service, the agent poller, local docker containers, or cross-project task load — call `mcp__mappa__meta_health` + `mcp__mappa__admin_status` (сервис жив, нагрузка) and `mcp__projects-meta__meta_system_snapshot` (поллер/докер/таски) instead of running `tasklist` / `docker ps` / guessing by hand. Triggers on «что запущено», «что сейчас крутится», «состояние системы», «состояние машины», «поллер работает?», «поллер живой?», «что с докером», «сводка по задачам», «what's running», «system status», «system snapshot», «is the poller up», «is the runner alive», «what containers are up». Read-only — no per-session grant needed. Skip for deep single-container docker diagnosis (that's using-vds-ops for the VDS / docker logs locally) and for mutating or precise per-task work (that's using-projects-meta / mappa task.*)."
---
# using-system-snapshot
## Overview
Two layers, one mental model: **mappa meta-service** (решение 14/15 — мета в сервисе) + **машина** (поллер/докер/таск-нагрузка — внешняя инфра).
1. Сервис жив и как загружен: `mcp__mappa__meta_health` (no args → `{ok}`) + `mcp__mappa__admin_status` (счётчики сущностей по типам/проектам — живая нагрузка).
2. Машина: `mcp__projects-meta__meta_system_snapshot` — поллер agents-task-runner, локальные docker-контейнеры, сводка таск-нагрузки из кэша.
Заменяет старый разброс `tasklist` / `docker ps` / ручного `meta_status` одной-двумя зондами.
**Core rule: never assert состояние сервиса, поллера, контейнеров или таск-нагрузки без вызова тула в этом же turn.** Память и «он же работал ранее» — не evidence.
## When to use
- Session start в **ops-контексте** — ориентация перед infra/раннер/борд-работой.
- User спрашивает что живо: «что запущено», «состояние системы», «поллер работает?», «что с докером», «what's running», «is the poller up».
- **Перед любым claim** о живости mappa-сервиса, поллера, контейнера или числа активных/блокированных тасок.
- Быстрый взгляд на таск-нагрузку (где сейчас сконцентрирована работа).
## When NOT to use
- Глубокая диагностика **одного** контейнера (logs/inspect/stats/restart-loop) — это using-vds-ops для Rusonyx VDS или `docker logs` локально.
- **Мутации** тасок или чтение полного борда/тела задачи — using-projects-meta (и mappa task.* / локальный `.tasks/` для текущего проекта).
- Библиотечные доки, поиск по коду — не сюда.
## Prerequisites
- `mcp__mappa__*` — mappa MCP (сервис meta; установка — setup-проект mappa).
- `mcp__projects-meta__meta_system_snapshot` — projects-meta-mcp (поллер/докер/кэш-таски). Если тула нет — `setup-projects-meta`.
## The calls
`mcp__mappa__meta_health` — no args, read-only. `{ok: true, service: "mappa"}` — сервис жив.
`mcp__mappa__admin_status` — no args, read-only. Счётчики по типам и проектам.
`mcp__projects-meta__meta_system_snapshot` — no args, read-only. Три ключа:
| Key | Shape | Liveness |
|---|---|---|
| `poller` | `{ running: bool, projects: "<owner/repo …>" }` | **live** на момент вызова |
| `docker` | `[{ name, status }]` — локальные контейнеры | **live** на момент вызова |
| `tasks` | `{ "<owner>/<repo>": { active, blocked }, … }` | **из кэша** projects-meta — может быть stale |
`docker` — **локальная** машина (включая `agents-task-runner-*`), НЕ VDS. `tasks` — кэш; для точного состояния — using-projects-meta Step 0 или mappa/локальный `.tasks/`.
## Output format — одна строка на секцию
Сожми в 3–4 строки, не дампи raw-object.
```
🟢 Mappa alive — 42 wiki / 18 tasks, 12 проектов
🟢 Poller running — OpeItcLoc03/skills (🔴 если running:false)
🟢 Docker — 8/8 up (иначе только проблемные)
📋 Tasks — 23 active / 41 blocked, 17 проектов (назвать 2–3 самых загруженных)
```
Правила на строку:
- **Mappa** — 🟢/🔴 + admin_status-сводка (счётчики по типам или проектам — кратко). Сервис упал = заголовок.
- **Poller** — 🟢/🔴 + running-flag + projects-строка. Остановлен — скажи прямо.
- **Docker** — если всё `Up` (вкл. `Up … (healthy)`) — `N/N up`. Иначе только проблемные (`Restarting`, `Exited`, `(unhealthy)`, `Created`, `Paused`) по имени + статусу.
- **Tasks** — суммы (Σ active / Σ blocked) + 2–3 проекта с наибольшей активностью. Полный расклад — только по запросу.
## What NOT to do
- **НЕ** утверждай «поллер работает» / «все контейнеры up» / «N активных тасок» по памяти или прошлому снапшоту. Зови тулы в текущем turn — liveness требует свежих данных.
- **НЕ** падай на `tasklist` / `docker ps` / ручной `meta_status` — это scatter, который скил заменяет. (`docker logs` — только для глубокой диагностики одного контейнера.)
- **НЕ** вставляй raw-JSON. Строки, по одной на секцию.
- **НЕ** подавай `tasks`-счётчики как точные — они из кэша. При важности точности — флаг сталезности + using-projects-meta.
## Common mistakes
| Mistake | Fix |
|---|---|
| «Сервис жив» без вызова в этом turn | Зови `meta_health`/`admin_status` — liveness требует текущих данных. |
| «Poller up» без вызова | `meta_system_snapshot` в текущем turn. |
| `docker ps` / `tasklist` вместо зондов | Один-два вызова тула; в этом смысл. |
| Читать снапшот-`docker` как VDS-флот | Это **локальная** машина. VDS — using-vds-ops. |
| `tasks`-счётчики как авторитетные | Они кэшированы. Точность — using-projects-meta Step 0 / mappa / `.tasks/`. |
| Дампить raw-объект | Сожми в строки (mappa / poller / docker / tasks). |

View File

@@ -1,169 +0,0 @@
# using-tasks
Runtime policy for keeping compressed working context across parallel tasks
in a monorepo. The agent reads and updates `.tasks/` so every session starts
oriented and every switch costs seconds, not minutes.
`using-tasks` governs the task board. **Канал — mappa** (решение 14/15): борд =
сущности `type=task` в сервисе (см. SKILL.md v2.0.0). Файловый `.tasks/` — легаси;
`setup-tasks` умер.
> Renamed from `task-status-wiki` at v1.0.0.
## When it triggers
- User is switching between tasks, resuming a paused task, starting a new
one, or asks "where were we" / "what's the status".
- User says: "use task management system", "pause", "switch to X",
"update status".
- Any context-switching or multi-task coordination question in a code
project.
- Борд читается из mappa (`entity_search(type='task', project=…)`);
файловый `.tasks/` — легаси, ничего настраивать не нужно.
## Structure
```
<monorepo-root>/
└── .tasks/
├── STATUS.md ← board: one block per task, sorted by priority
└── <task-slug>.md ← deep context per task, one file each
```
Commit `.tasks/` to git — decision history is valuable, diffs show how
thinking evolved.
## STATUS.md format
```markdown
# Task Board
_Updated: YYYY-MM-DD_
## 🔴 [task-slug] — short description
**Status:** active | paused | blocked | done
**Where I stopped:** one sentence — the exact thought or action interrupted
**Next action:** one concrete step to resume immediately
**Blocker:** (only if blocked) what is preventing progress
**Branch:** git branch name
---
```
Status legend:
| Emoji | State | Notes |
|---|---|---|
| 🔴 | Active | Currently worked on. **Only one at a time.** |
| 🟡 | Paused | In progress, resumable. |
| ⚪ | Ready | Defined, not started. |
| 🟢 | Done | Kept until merged. |
| 🔵 | Blocked | Waiting on external input. |
## Per-task file format (`<task-slug>.md`)
Sections, in order: **Goal** (one paragraph — what this achieves and why),
**Key files** (`path/to/file.ts:42` style — specific lines when relevant),
**Decisions log** (reverse-chronological, append-only — past entries are
immutable), **Open questions**, **Completed steps**, **Notes** (temporary
hypotheses, links).
## Operations
### Session start
1. Check the mappa board: `entity_search(type='task', project=<имя>)`.
Файлового `.tasks/STATUS.md` больше нет — setup-tasks умер.
2. Read `STATUS.md`.
3. If user names a task, read its `<task-slug>.md`.
4. Confirm in one sentence: "We're in the middle of X, next step is Y."
5. Ask if the plan is still correct before doing anything.
6. If `_Updated` is more than 3 days old, flag it and ask the user to
confirm current state.
### Session end / pause / switch
1. Update `STATUS.md`: set the current task to 🟡, refresh "Where I stopped"
and "Next action".
2. Append non-obvious decisions to `<task-slug>.md` Decisions log.
3. Move finished items to "Completed steps".
4. Commit: `git add .tasks/ && git commit -m "chore: update task status [<task-slug>]"`.
### Task switch
1. Run session-end ops for the current task.
2. Read the target `<task-slug>.md`.
3. Set the target to 🔴 in `STATUS.md` (demote previous active to 🟡).
4. Confirm orientation before starting work.
### New task
1. Ask: slug, goal, known key files, branch.
2. Create `<task-slug>.md` with Goal and Key files populated.
3. Add a ⚪ block to `STATUS.md`.
4. Create / checkout the branch if missing.
### Task completion
1. **Pre-close coverage check** — list acceptance criteria, locate
evidence (tests, smoke-test artefacts, manual checklist ticks, design
doc refs). Missing evidence → ask the user before closing; never auto-close.
2. Resolve or drop all open questions.
3. Set status to 🟢 in `STATUS.md`.
4. Append a final summary line to the Decisions log.
5. Remind the user to delete the branch after merge.
### Post-commit task closure prompt
After a `feat:` / `fix:` commit the agent prompts:
"эта работа закрывает таску `<slug>`?". Slug candidates: commit-message
scope, current branch, most recent `Where I stopped`. If yes → run the
coverage check above. Skips `chore:` / `meta:` / `docs:` commits.
Forces a fresh-while-fresh decision, instead of letting shipped code sit
under a stale ⚪ block.
### Recommendations / "what's next" trigger
When the user asks «что дальше», «срочные», «куда копаем», "what next",
"status", or on session-start — recommend in this order:
1. **Local cwd-project board** ranked 🔴 → 🟡 → ⚪. Cite slugs.
2. **One footnote line** if relevant: `Cross-project: N 🔴 in other repos
(см. mcp__projects-meta__tasks_aggregate).` Only if N>0 and no local 🔴.
Explicit "по всем проектам" / "across all projects" flips the order.
Pairs with `using-projects-meta`'s local-first rule (which covers reads;
this one covers recommendations).
## Rules
- **Never lose "Where I stopped".** Most critical field. If unclear, ask
before ending the session.
- **One sentence per `STATUS.md` field.** Compress, don't write prose.
- **Key files must be specific** — not "auth module" but
`packages/auth/src/useAuth.ts:87`.
- **Decisions log is append-only.** Past entries are immutable.
- **Commit after every session end.** `git log` is the history of thinking.
- **Always confirm orientation at session start.** State understanding
before acting.
- **One active task at a time** — only one 🔴 in `STATUS.md`.
- **Never close without coverage check.** See "### Task completion"
step 1.
- **Local-first recommendations.** cwd-project first; cross-project at
most one footnote line.
## Install
From the repo root:
```bash
bash scripts/install.sh using-tasks
```
Works on Windows under git-bash, Linux, macOS.
## See also
- mappa — сервис-хост борда (`task_create`/`task_claim_next`/`task_close`,
per-type `t:N`).
- [`project-bootstrap`](../project-bootstrap/) — mappa-режим для новых проектов.

View File

@@ -1,138 +0,0 @@
---
name: using-tasks
author: ours
version: 2.0.0
description: >
Policy skill for working with the project task board in Mappa (решения 14/15:
мета в сервисе). Use whenever switching between tasks, resuming a paused task,
starting a new task, asking «where were we», says «use task management system»,
«pause», «switch to X», «what's the status», «update status», or tracking
progress across parallel workstreams. Board = сущности `type=task` в mappa
(чтение — карв-аут лиза; мутации — под лизом проекта, решение 19). Файловый
`.tasks/` — легаси; `setup-tasks` умер (нечего настраивать).
---
# using-tasks
> Policy для поддержания сжатого рабочего контекста параллельных тасок.
> Борд проекта — сущности mappa: каждая таска `t:N` (per-type номер, решение 20)
> со статусом `ready|active|paused|blocked|done`, телом, owner'ом и рёбрами
> ([[refs]] → parent_of/ref, решения 4/6). Чтение — карв-аут лиза (решение 19);
> **любая мутация — под лизом проекта**.
## MCP-поверхность
| Операция | Тул | Примечание |
|---|---|---|
| Взять следующую ready-таску | `mcp__mappa__task_claim_next(project, owner)` | атомарно: лиз + таска; → `{ok, token, task}` |
| Продлить лиз | `mcp__mappa__task_heartbeat(project, claim_token)` | долгие таски |
| Создать таску | `mcp__mappa__task_create(project, slug, title?, description?, status?, claim_token)` | под лизом |
| Закрыть таску | `mcp__mappa__task_close(project, id, claim_token)` | под лизом |
| Прочитать таску | `mcp__mappa__entity_get(id)` | id internal из search/claim |
| Список борда | `mcp__mappa__entity_search(q, type='task', project=<имя>, limit)` | все статусы |
| Дерево parent_of | `mcp__mappa__graph_tree(root, depth?, fields?, limit?)` | зонтики/иерархия (решение 6) |
| Связанные сущности | `mcp__mappa__graph_neighbors/backlinks(id)` | рефы к таске |
| Уведомление при закрытии | `mcp__mappa__inbox_send(project=<notify>, from=<своя>, subject, body)` | письмо комиссионеру |
**Лиз = лок на запись (решение 19).** Одна строка leases на проект: если другой
агент держит лиз — `task_claim_next` вернёт **422 busy**. Это серверный аналог
старого `.tasks/.lock`: проверять «а не поллер ли работает» руками не нужно —
сам claim скажет. Чтения лиза не требуют.
**Рефы и id (#1037).** Таски наружу несут `ref: "t:N"` первым полем, `num`
следом, глобальный `id` — internal (последним, для addressing в тулах).
Ссылайся на таску `[[t:N]]` (в body → рёбра автоматически), никогда
`#<глобальный id>`.
## Статусы (эмодзи для презентации)
| Эмодзи | Статус | Значение |
|---|---|---|
| ⚪ | `ready` | не начата, полностью определена |
| 🔴 | `active` | в работе (обычно одна) |
| 🟡 | `paused` | в процессе, возобновляема |
| 🔵 | `blocked` | ждёт внешнего входа |
| 🟢 | `done` | закрыта |
## Операции агента
### Ориентация (session start)
1. **Инбокс-свип** — `mcp__mappa__inbox_monitor(project=<имя>)`: непрочитанные
письма могут менять план. Обработай каждое по `inter-session-messaging`.
2. **Борд** — `mcp__mappa__entity_search(q='', type='task', project=<имя>, limit=50)`:
отсортируй по статусу (🔴 → 🟡 → ⚪), по одной строке на таску, цитируй slug.
3. Если user назвал таску — `entity_get(id)` по её рефу/номеру.
4. Подтверди одним предложением: «Мы в середине X, следующий шаг — Y».
5. Спроси, верен ли план, перед действиями.
### Переключение / пауза / конец сессии
1. Текущая 🔴 → `task_close` если завершена (см. закрытие), иначе пометь
`status=paused` через update-механику (owner остаётся; «where stopped» —
в body или handoff).
2. **Инбокс-свип** на границе тасок (`inbox_monitor`).
3. Возьми следующую: `task_claim_next` (лиз + таска). Прежняя остаётся 🟡.
4. Подтверди ориентацию перед стартом.
> Примечание про «Where I stopped»: у mappa-таски нет отдельного поля — держи
> место остановки в `description` (последний абзац) или, для сессионного
> контекста, в **handoff-сущности** (`session-handoff`: summary/open_treks).
> Перед концом сессии обязательно запиши handoff — это аналог
> «Never lose Where I stopped».
### Создание таски
1. **Через тул, не руками** (решение 20): сначала лиз (`task_claim_next`) →
`task_create(project, slug, title, description, status='ready', claim_token)`.
Номер `t:N` назначает сервер — не выдумывай.
2. Slug: kebab-case, латиница. Description: markdown, `[[refs]]` на связанное.
3. Закрыть лиз не нужно — экспирится по TTL; мутации идут одним циклом.
### Закрытие таски
1. **Pre-close coverage check.** Собери acceptance criteria из description.
Для каждого — evidence: тест в диффе, артефакт, ссылка на дизайн.
Нет evidence на критерий → спроси user'а «закрывать или подождать coverage'а».
2. Resolve/drop открытые вопросы.
3. `task_close(project, id, claim_token)` → статус `done`.
4. **Notify-письмо (кросс-проектные таски).** Если таска пришла из другого
проекта (в description/meta есть `from:`/`notify:`) — `inbox_send`
комиссионеру: `project=<notify>`, `subject="[event: closed] <slug>"`,
body = итог (сделано, acceptance, ссылки). Живая сессия пишет сама.
5. Дополни summary-строку в handoff/вики при наличии.
### Рекомендации / «что дальше»
User спросил «что дальше», «status», «куда копаем» — рекомендую в порядке:
1. **Локальный борд текущего проекта** (cwd): `entity_search(type='task',
project=<имя>)` — 🔴 → 🟡 → ⚪, по строке на таску, цитируй slug.
2. Одна footnote-строка если кросс-проектно релевантно: `Cross-project: N 🔴
active (см. mcp__projects-meta__tasks_aggregate).` Только если N>0 и в cwd
нет активной 🔴.
Кросс-проектные ургенты — информация, не драйвер «что делать здесь».
## Правила
- **Лиз-дисциплина.** Мутации — только под лизом; 422 busy = кто-то другой
пишет, не параллель.
- **Never lose Where I stopped** — критичное поле: в description + handoff.
- **Одна активная таска** — только одна 🔴 на проект.
- **Не выдумывай номера** — `t:N` назначает сервер.
- **Never close без coverage check** — evidence на каждый acceptance criterion,
иначе спросить.
- **Notify-письмо при закрытии** кросс-проектных тасок — статус 🟢 ≠ комиссионер
узнал.
- **Чтения — карв-аут.** `entity_search`/`entity_get`/`graph_*` не требуют лиза
и не блокируются чужим лизом.
- **Локально-первая рекомендация** — борд cwd первым; кросс-проект — футонота.
- **Ссылайся `[[t:N]]`**, не глобальным id (#1037).
## Legacy (переходное)
Файловый `.tasks/` (STATUS.md + per-task файлы) — легаси-канал, живёт пока
миграция/поллер не доедут. Не смешивай: новые таски — через mappa task_create;
старые борды читай напрямую (`.tasks/STATUS.md`), если они ещё в файлах.
`setup-tasks` умер — файловые борды больше не настраиваются.

View File

@@ -1,92 +0,0 @@
---
name: using-wiki-graph
author: ours
version: 1.0.0
description: >
Use when a question is RELATIONAL about a wiki or any entities in Mappa —
«что связывает X и Y», «как связаны», «путь между X и Y», «what connects X
and Y», «shortest path» — or about STRUCTURE/HEALTH — «что ссылается на X»,
«backlinks of X», «сироты», «битые ссылки», «orphan pages». Triggers
`mcp__mappa__graph_neighbors|graph_backlinks|graph_path|graph_stats` —
детерминированный BFS по рёбрам графа на стороне сервиса (решение 4/7:
[[refs]] в body → рёбра). Guarded failure-mode: на реляционные вопросы агент
читает одну страницу и ОСТАНАВЛИВАЕТСЯ, никогда не ходит по многохоповым
цепочкам сам. Адресация — internal id (из wiki_get/entity_search); ответы
несут per-type refs (t:N/i:N/w:N, решение 20/#1037). Read-only, без лиза
(карв-аут, решение 19). Skip для одно-страничных контентных вопросов.
---
# using-wiki-graph
Stop and call the graph. On a **relational** or **structural** question about
wiki-страницы или любые сущности mappa (таски, письма, сессии), не отвечай,
прочитав одну страницу — связи образуют граф, который LLM не обходит надёжно
чтением. Сервис ходит по рёбрам детерминированно (BFS) и возвращает ответ в
нескольких строках; контекст не засоряется.
## When to use
Вопрос о **связях между сущностями** или **структуре графа**, не о содержании
одной страницы:
- relational — "what connects X and Y", "path between X and Y", «что связывает»,
«как связаны», «путь между»;
- neighbourhood — "neighbours of X", «соседи X», «что рядом с X»;
- incoming — "what links to X", "who references X", «кто ссылается на X»,
«backlinks»;
- health — "orphan pages", "dangling links", «сироты», «битые ссылки»,
«здоровье вики».
## Precondition — граф реально связан
Граф полезен, когда рёбра есть. Если сомневаешься — сначала
`mcp__mappa__graph_stats()`: `edges` ≈ 0 ⇒ граф пуст, отвечай чтением.
(Слаги без [[линков]] рёбер не создают; сироты — норма для разреженных вики.)
## Адресация: slug → id (internal)
Тулы graph принимают **internal id** (SQL PK), который наружу помечен internal
(решение 20/#1037). Резолв:
1. `mcp__mappa__wiki_get(project, slug)` (или `entity_search(q, type='wiki')`) —
из ответа бери `id` (последнее поле; публичные `ref`/`num` — для показа).
2. Передавай `id` в graph-тулы.
3. Ответы graph несут `ref` (t:N/i:N/w:N) на узлах и рёбрах (`from_ref`/`to_ref`)
— реферируй по ним в ответе, не по id.
## Steps
1. Выбери тул по форме вопроса:
- relational / "what connects" → `mcp__mappa__graph_path({from, to})` —
кратчайшая неориентированная цепочка.
- neighbourhood → `mcp__mappa__graph_neighbors({id})` — исходящие рёбра
узла с резолвом целей (to_ref/kind).
- "who links to" → `mcp__mappa__graph_backlinks({id})` — входящие рёбра.
- health → `mcp__mappa__graph_stats()` (nodes/edges/components); сирота
конкретной страницы = `graph_backlinks(id)` пусто.
2. Резолвь id (см. выше), зови graph, отдавай цепочку/список как есть.
3. Пустой `path` = связи реально нет — так и скажи; не выдумывай цепочку
из текстовой близости.
## Failure modes
- Страница удалена/не найдена → graph тул вернёт ошибку. Проверь `wiki_get` —
возьми свежий id.
- Разреженный граф → `stats` показывает ~0 edges. Не форсируй — читай.
- Нет MCP-тулов mappa в сессии → граф недоступен; читай вручную, отметь
пользователю, что mappa MCP не подключён.
## Side effects
None. Read-only (карв-аут лиза, решение 19): без лиза, без записи, без сети
кроме сервиса.
## What NOT to do
- Не отвечай на реляционный вопрос чтением одной страницы — это тот самый
0%-recall провал, ради которого скил существует.
- Не тащи всю вики в контекст, чтобы «проследить» связи руками — сервис делает
это за ноль токенов.
- Не зови graph на контентные вопросы ("что такое X") — это чтение, не граф.
- Не передавай слаги/пути в graph-тулы — только internal id, и только свежие
(удалённая сущность → ошибка).

View File

@@ -1,183 +0,0 @@
# using-wiki
Runtime policy for an LLM Wiki built on the
[Karpathy LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).
Knowledge is **compiled once and kept current** across three layers, via
three named operations, with strict file formats that keep the wiki
parseable and grep-friendly.
`using-wiki` governs *usage* of an existing `.wiki/`. Initial creation and
**Канал — mappa** (решение 14/15): вики = сущности `type=wiki` в сервисе
(см. SKILL.md v2.0.0). Файловый `.wiki/` — легаси; `setup-wiki` умер.
> Renamed from `wiki-maintainer` at v1.0.0.
## When it triggers
- User says: "use project wiki", "query the wiki", "ingest this", or the
Russian equivalents ("обнови вики", "проверь вики", "запроси вики",
"заингесть").
- Any time the agent modifies a file under `.wiki/` — the workflow and
formats below are mandatory.
- If `.wiki/` is missing or non-canonical, this skill delegates to
вики читается из mappa (`wiki_get`); ничего настраивать не нужно.
## Three layers (do not blur)
1. **Raw sources** — `.wiki/raw/` (or external paths registered in
`raw/README.md`). **Immutable.** Read, never edit. The only exception is
appending a `> Status` blockquote when the user explicitly asks for a
status audit.
2. **Wiki** — everything else under `.wiki/`. Agent-owned. Entity / concept /
package / source summary pages.
3. **Schema** — `.wiki/CLAUDE.md`. Project-specific conventions (what
entities, what packages, naming). Always read it first; it overrides this
skill on conflict.
## Three operations
### Ingest
«заингесть X» — pull a raw source into the wiki.
1. Read the raw source fully.
2. Extract: entities, concepts, packages, cross-cutting patterns.
3. Create `sources/<slug>.md` (one summary page per source, ~50–150 lines).
4. For each affected entity / concept / package page: update if exists,
create if not. Flag contradictions explicitly with
`> **Противоречие:** источник A говорит X, источник B — Y`.
**Never silently overwrite.**
5. Update `index.md`.
6. Append one line to `log.md`.
7. Report: what was created, updated, contradicted.
One ingest may touch 10–15 pages. That's normal — that's why an LLM does it.
### Query
A question answered from the wiki.
1. Read `index.md` first, drill into relevant pages.
2. Answer with citations as markdown links.
3. **Compound the wiki.** If the answer is a real synthesis, ask the user:
"Сохранить как страницу wiki?" Good queries become durable pages under
`concepts/` or `analyses/`.
4. Append one line to `log.md`.
### Lint
«проверь wiki» — health check.
Scan for:
- Contradictions between pages.
- Orphans (pages with no inbound links).
- Stale claims (raw source updated after the summary's `ingested:` date —
check via `git log -p`).
- Concepts mentioned in prose but missing their own page.
- Empty / TODO sections.
Report as a punch list. Don't delete anything automatically. Append one
line to `log.md` with the findings.
## File formats (mandatory)
### Page frontmatter
```yaml
---
title: Человекочитаемое имя
type: entity | concept | package | source | contradiction | open-question | overview
tags: [short, tokens]
sources: [../sources/foo.md, ../sources/bar.md]
updated: 2026-04-21
---
```
Source pages also carry `ingested: YYYY-MM-DD` and `raw_path: ../raw/...`.
Contradiction pages also carry `status: open | resolved | accepted-divergence` and `affects: [../entities/x.md, ../concepts/y.md]`.
Open-question pages also carry `status: open | answered | obsolete` and `touches: [../entities/x.md, ../sources/z.md]`.
### File naming
- `kebab-case.md`, **Latin only**. Transliterate Cyrillic / non-Latin in
filenames; keep the original title in H1 + frontmatter.
- `entities/<name>.md`, `concepts/<name>.md`, `packages/<name>.md`
(no `@org/` prefix), `sources/<slug>.md`, `contradictions/<slug>.md`,
`open-questions/<slug>.md`.
### `log.md` — append-only, grep-parseable
Every entry must start with:
```
## [YYYY-MM-DD] <operation> | <short description>
```
Operations: `ingest`, `query`, `lint`, `refactor`, `decision`, `init`.
Parse with: `grep "^## \[" .wiki/log.md | tail -20`.
### `index.md`
Catalog, not narrative. One line per page: `- [Title](path) — hook.`
Sections by type. Update on every ingest.
### Cross-references
- Wiki → wiki: relative markdown links — `[Name](../entities/x.md)`.
- Wiki → code: relative path from repo root — `[foo.js](../../packages/api/foo.js)`.
- Wiki → raw: `../raw/<file>`.
- URL-encode spaces (`%20`) and Cyrillic when needed.
## Quick reference
| Situation | Files touched |
|---|---|
| Ingest one doc | `sources/<slug>.md` (new) + 3–15 entity/concept/package pages + `index.md` + `log.md` |
| Query | (read only) + optionally a new wiki page + `log.md` |
| Lint | (read only) + `log.md` |
| Новая вики проекта | первый ingest создаёт CLAUDE/index/log через wiki_create |
## Common mistakes
- **Editing `raw/`.** Don't. Only allowed change: status blockquote on
explicit request.
- **Dumping raw content into `sources/`.** Summaries are summaries. Link to
raw, don't copy.
- **Silent overwrites on contradictions.** Flag them with a `> **Противоречие:**`
block.
- **Narrative `log.md`.** "Today I added…" is wrong. Use
`## [YYYY-MM-DD] ingest | <what>`.
- **Non-ASCII filenames.** Breaks greppability and cross-platform. Transliterate.
- **Forgetting `index.md`.** Pages not listed there are invisible to future
queries.
- **Improvising layout when canon files are missing.** Hand off to
(setup-wiki умер: канал — mappa, страницы создаются wiki_create).
## When NOT to use
- The project has CLAUDE.md / AGENTS.md docs but no `.wiki/` — that's regular
documentation, not an LLM Wiki.
- The user wants a single-file README or ADR — this skill is for persistent,
interlinked knowledge bases.
- One-off questions about code — read files directly, no wiki workflow needed.
## Install
From the repo root:
```bash
bash scripts/install.sh using-wiki
```
Works on Windows under git-bash, Linux, macOS.
## See also
- mappa — сервис-хост вики (`wiki.get`/`wiki.create`/`wiki.update`);
canon migration.
- [`project-bootstrap`](../project-bootstrap/) — invokes mappa-режим для
new projects.
- Karpathy's LLM Wiki gist:
<https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f>

View File

@@ -1,202 +0,0 @@
---
name: using-wiki
author: ours
version: 2.0.0
description: >
Policy skill for working with the project wiki in Mappa (Karpathy LLM Wiki
pattern, channel = mappa-сущности, решения 14/15 спеки mappa). Use when the
user asks to ingest a document, answer from the wiki, lint/health-check it, or
says «use project wiki», «обнови вики», «проверь вики», «запроси вики»,
«заингесть», «query the wiki». Also use when modifying any wiki page — the
workflow and formats below are mandatory, and project-specific conventions live
in the `CLAUDE` wiki-сущности проекта. Wiki = сущности `type=wiki` в сервисе
(чтение — карв-аут лиза; запись — под лизом проекта, решение 19). Файлового
`.wiki/` больше нет; `setup-wiki` умер (нечего настраивать).
---
# using-wiki
> Policy for maintaining an LLM Wiki (Karpathy pattern:
> https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) whose pages
> live in **Mappa** as `type=wiki` сущности (решение 14/15), not in files.
> Knowledge is **compiled once and kept current**: three named operations
> (ingest / query / lint), strict page formats that keep the wiki parseable and
> grep-friendly, and a cross-linked graph ([[refs]] → рёбра, решение 4).
## Prerequisites
Wiki проекта = сущности в сервисе Mappa (HTTP-ядро, MCP-адаптер `mcp__mappa__*`).
Слаг страницы = путь от корня вики без расширения (`index`, `log`, `CLAUDE`,
`concepts/foo`, `entities/bar`, `packages/baz`, `sources/doc`, `overview`).
Body = frontmatter + markdown как есть (content-модель сохраняется, решение 2).
Проектная вики (scope=project) читается/пишется с параметром проекта;
общая вики (scope=shared) — без проекта. Чей именно вики трогаем, определяет
контекст: `wiki.get(project, slug)` — проектная, `wiki.get(slug)` — shared.
Файловый `.wiki/` в репозиториях — легаси: источник истины — сервис.
Если вики проекта пуста (нет сущностей) — **ничего настраивать не надо**
(setup-wiki умер): первый ingest сам создаёт `CLAUDE`, `index`, `log` (см. Ingest).
## MCP-поверхность
| Операция | Тул | Примечание |
|---|---|---|
| Чтение страницы | `mcp__mappa__wiki_get(project?, slug)` | чтение — карв-аут лиза (решение 19) |
| Поиск страниц | `mcp__mappa__entity_search(q, type='wiki', project?, scope?, limit)` | ILIKE по body/title |
| Захват лиза для записи | `mcp__mappa__task_claim_next(project, owner)` | → `token` (лиз проекта, решение 19); таска может отсутствовать |
| Продление лиза | `mcp__mappa__task_heartbeat(project, claim_token)` | долгие ingest-циклы |
| Создать страницу | `mcp__mappa__wiki_create(project, slug, body, claim_token)` | под лизом |
| Обновить страницу | `mcp__mappa__wiki_update(project, id, title?, body?, claim_token)` | под лизом; id — internal (см. ниже) |
**Запись всегда под лизом.** Мутации wiki гейтятся лизом проекта: без
валидного `claim_token` — 422 busy. Лиз экспирится по TTL (дефолт 600s);
закрыть вручную нечем (кроме `admin_release_lease` для залипших) — пиши,
затем отпусти (не держи лиз на время чтения/размышлений).
**Рефы и id (#1037).** Публичная поверхность несёт per-type реф первым полем:
`ref: "w:3"` (тип+номер, решение 20), `num` следом, глобальный `id` — internal
(последним полем). Для `wiki.update` нужен internal `id` — бери его из ответа
`wiki_get`/`entity_search`. В тексте страниц ссылайся викилинками по слагу
(`[[concepts/foo]]`, решение 4) или per-type рефами (`[[i:N]]`/`[[t:N]]`).
## Три слоя (не смешивать)
1. **Raw-источники** — `sources/<slug>` страницы. Иммутабельны: читай, не
редактируй (единственное исключение — блок-цитата `> Status` по явной
просьбе пользователя).
2. **Вики** — все остальные страницы (entities/concepts/packages/…).
3. **Схема** — сущность `CLAUDE` (slug `CLAUDE`). Конвенции проекта. Читай её
первой; она перекрывает этот скил при конфликте.
## Первый шаг любой операции
1. `mcp__mappa__wiki_get(project, 'CLAUDE')` — если есть, читай (схема).
2. `mcp__mappa__wiki_get(project, 'index')` — каталог, найди нужные страницы.
3. Только потом действуй.
Если `CLAUDE` нет — вики либо новая, либо неухоженная: не импровизируй
структуру, создай `CLAUDE`/`index`/`log` при первом ingest (см. ниже).
## Три операции
### Ingest — «заингесть X»
1. Прочитай источник полностью.
2. Извлеки: entities, concepts, packages, кросс-резы.
3. Создай `sources/<slug>` — одну страницу-резюме на источник (~50–150 строк;
ссылку на raw клади в frontmatter `raw_path` + `ingested:`).
4. Для каждой затронутой страницы:
- есть → обнови (`wiki_update(project, id, body, claim_token)`). **Противоречия
помечай явно** блоком `> **Противоречие:** источник A говорит X, источник B — Y`.
Не затирай молча.
- нет → создай (`wiki_create`).
5. Обнови `index` (каталог: одна строка на страницу).
6. Допиши одну строку в `log` (формат ниже).
7. Отчитайся пользователю: что создано, что обновлено, какие противоречия.
**Один ingest может затронуть 10–15 страниц. Это нормально — для того LLM и нужны.**
Порядок записи: сначала лиз (`task_claim_next`), затем все wiki-мутации одним
циклом (не бери лиз на чтение), затем отпусти (лиз живёт TTL — просто закончи
писать; heartbeat только если цикл реально долгий).
### Query — вопрос по вики
1. Читай `index` сначала, затем углубляйся в страницы (`wiki_get` по слагу).
2. Отвечай с цитатами-викилинками: `[[concepts/foo]]` (рёбра создаются при
записи, решение 4).
3. **Компаундируй вики.** Если ответ — реальный синтез (сравнение, анализ,
новая связь) — спроси пользователя: «Сохранить как страницу wiki?» Хорошие
вопросы становятся страницами в `concepts/`.
4. Допиши строку в `log`.
### Lint — «проверь вики»
Ищи:
- **Противоречия** между страницами.
- **Сирот** — страницы без входящих ссылок: `mcp__mappa__graph_backlinks(id)`
(id из `wiki_get`) → нет входящих рёбер = сирота (подробнее — using-wiki-graph).
- **Stale-claims** — `updated_at` страницы старше источника, который она резюмирует.
- **Потерянные сущности** — понятия из текста без своей страницы
(`entity_search` по имени → пусто).
- **Пустые/TODO-секции.**
Отчёт — панч-лист. Ничего не удаляй автоматически.
Допиши строку в `log` с итогом.
## Форматы страниц (ОБЯЗАТЕЛЬНО)
### Frontmatter
```yaml
---
title: Человекочитаемое имя
type: entity | concept | package | source | contradiction | open-question | overview
tags: [short, tokens]
sources: [concepts/mappa.md]
updated: 2026-08-24
---
```
Страницы `sources/` дополнительно несут `ingested: YYYY-MM-DD` и `raw_path: …`.
`contradictions/` — `status: open | resolved | accepted-divergence` и `affects:`.
`open-questions/` — `status: open | answered | obsolete` и `touches:`.
### Слаги
- `kebab-case`, **только латиница**. Кириллицу/др. скрипты транслитерируй
(`план переписывания` → `ozon-client-rewrite`). Оригинальный title — в H1 и frontmatter.
- `entities/<name>`, `concepts/<name>`, `packages/<name>`, `sources/<slug>`,
`contradictions/<slug>`, `open-questions/<slug>`.
### `log` — append-only, grep-parseable
Каждая запись **обязана** начинаться с:
```
## [YYYY-MM-DD] <operation> | <short description>
```
Операции: `ingest`, `query`, `lint`, `refactor`, `decision`, `init`.
Парсится: `entity_search(q="## [", type="wiki", project=…)` по сущности `log`.
### `index`
Каталог, не нарратив. Одна строка на страницу: `- [Title](concepts/foo.md) — hook.`
Секции по типам. Обновляется на каждом ingest.
## Quick reference
| Ситуация | Что трогаем |
|---|---|
| Ingest одного документа | `sources/<slug>` (новая) + 3–15 entities/concepts/packages + `index` + `log` |
| Query | (чтение) + возможно новая страница + `log` |
| Lint | (чтение) + `log` |
| Новая вики проекта | первый ingest создаёт `CLAUDE`/`index`/`log` + контент |
## Частые ошибки
- **Правка `sources/`.** Нельзя. Только статус-блок по явной просьбе.
- **Дамп сырья в `sources/`.** Резюме — это резюме. Ссылайся на raw, не копируй.
- **Молчаливые перезаписи.** Новый источник противоречит странице — пометь
блоком `> **Противоречие:**`; не затирай.
- **Нарративный `log`.** «Сегодня я добавил…» — неверно. Формат:
`## [YYYY-MM-DD] ingest | <что>`.
- **Не-ASCII слаги.** Ломают grep и кросс-платформенность. Транслитерируй.
- **Забытый `index`.** Страницы без записи в каталоге невидимы для будущих query.
- **Пропущенные противоречия в lint.** Ценность вики — в вскрытых напряжениях,
а не в ложном консенсусе.
- **Запись без лиза.** Wiki-мутации без `claim_token` → 422 busy; не пытайся
писать «напрямую».
- **Держать лиз на чтение/раздумья.** Лиз — на время записи. Чтение — карв-аут.
## Когда НЕ использовать этот скил
- Проект без вики в mappa (нет сущностей `type=wiki`) — обычная документация,
не LLM Wiki.
- Пользователь хочет однофайловый README/ADR — скил для персистентной
связной базы знаний.
- Разовые вопросы по коду — обычное чтение файлов, не вики-воркфлоу.
- Реляционные/структурные вопросы о вики (связи, сироты, пути) — это
**using-wiki-graph** (`mcp__mappa__graph_*`).

View File

@@ -1,7 +1,7 @@
--- ---
name: writing-skills name: writing-skills
adapted-from: obra/superpowers @ 6.2.0 (MIT) — TDD-for-skills core; ideya 8 self-skill-authoring (workshop record) adapted-from: obra/superpowers @ 6.2.0 (MIT) — TDD-for-skills core; ideya 8 self-skill-authoring (workshop record)
version: 0.1.1 version: 0.2.0
description: > description: >
Authoring agent skills TDD-style — RED-GREEN-REFACTOR applied to SKILL.md Authoring agent skills TDD-style — RED-GREEN-REFACTOR applied to SKILL.md
documents. Use when creating a new skill, editing an existing one, or documents. Use when creating a new skill, editing an existing one, or
@@ -89,9 +89,21 @@ content for hypothetical cases.
### Skill structure (our catalog conventions) ### Skill structure (our catalog conventions)
``` ```
skills/<name>/SKILL.md skills/<name>/SKILL.md # общий каталог (catalog, версионируется, ставится install.sh)
``` ```
**Куда класть скил — определи ДО написания (три варианта, не путать):**
| Тип скила | Место | Когда |
|---|---|---|
| Общий каталог | `~/projects/skills/skills/<name>/SKILL.md` + deploy (lint/build/install) | полезен всем проектам/агентам |
| **Проектный (зона проекта)** | `<project>/.agents/skills/<name>/SKILL.md` (pi грузит из cwd; Claude Code: `.claude/skills/`) | привязан к одному проекту/роли (пример: `.admin` ops-скилы, `books/.agents/skills/`) |
| ~~Глобальная установка руками~~ | ~~`~/.agents/skills/`~~ | **НЕ сюда** — это установочная копия (перезапишется update-skills), не место разработки |
Правило: если скил про зону одного проекта (admin, books, …) — проектный путь
(`.agents/skills/` в cwd проекта), НЕ общий каталог и НЕ `~/.agents/skills/`.
Если скил общий — каталог `skills/` + deploy-цикл. При сомнении — спросить.
Frontmatter (YAML): Frontmatter (YAML):
- `name` — letters, numbers, hyphens only. Verb-first, active voice: - `name` — letters, numbers, hyphens only. Verb-first, active voice:
@@ -158,6 +170,8 @@ discipline skills.
- [ ] Description = when to use only, no workflow summary - [ ] Description = when to use only, no workflow summary
- [ ] Frontmatter: name (verb-first, hyphens), description (triggers), version - [ ] Frontmatter: name (verb-first, hyphens), description (triggers), version
(bumped), provenance (author/adapted-from with real pin) (bumped), provenance (author/adapted-from with real pin)
- [ ] Placement decided: project skill → `<project>/.agents/skills/` (cwd), NOT
`~/.agents/skills/`; catalog skill → `skills/<name>/` + deploy cycle
- [ ] Lint passes (catalog: `scripts/lint-skills.py`), dist rebuilt - [ ] Lint passes (catalog: `scripts/lint-skills.py`), dist rebuilt
(`scripts/build.sh`), installed (`scripts/install.sh <name>`) (`scripts/build.sh`), installed (`scripts/install.sh <name>`)
- [ ] README provenance table updated (catalog) - [ ] README provenance table updated (catalog)