claude-skills/.wiki/log.md

# Wiki Log

Append-only operation log. One entry per operation. Format:

```
## [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.