Commit Graph

354 Commits

Author SHA1 Message Date
d173d583ff meta(tasks): create [session-ritual-context7-pins-review] in OpeItcLoc03/skills 2026-08-12 16:48:21 +00:00
43988f57ba meta(tasks): close diagnosing-bugs-writing-skills-review (VERDICT PASS) 2026-08-12 18:28:49 +03:00
11c083918c feat(review-kit-pi-method): v0.1.0 — pi-native clean-context review subagent spawn (verified live on pi 0.84.1: -nc -ns -nt = unprompted) 2026-08-12 18:25:05 +03:00
5b709d3767 meta(tasks): normalize STATUS.md line endings to LF (repo convention) 2026-08-12 17:13:55 +03:00
f6a41ce69e meta(tasks): close brainstorming-skill-review (VERDICT PASS 6/6) 2026-08-12 17:12:55 +03:00
4e38639647 meta(tasks): create [brainstorming-skill-review] in OpeItcLoc03/skills 2026-08-12 14:04:32 +00:00
eab171308e meta(tasks): close using-tasks-archive-path-fix (bff9c62) 2026-08-12 16:48:42 +03:00
bb113c6cfb meta(tasks): close de-superpowers-skill-readmes + skills-live-claudemd-superpowers-trigger
Both review follow-ups (F4/F5) done by workshop session; F1/F2 already
closed upstream by reviewer. Notify: OpeItcLoc03/workshop.
2026-08-12 16:46:33 +03:00
94af375ec4 meta(tasks): close sovereign-catalog-wave2-review + 4 follow-ups
VERDICT PASS (wave-2 range) + CONCERN on HEAD (42ed5ea defects):
- review closed: evidence in .workshop/.brainstorm/sovereign-catalog-wave2-review.md
- follow-ups created: project-discipline-dist-rebuild, project-discipline-description-contradiction,
  de-superpowers-skill-readmes, skills-live-claudemd-superpowers-trigger
- F1/F2 already fixed upstream d7903c3 (workshop) → closed done
- commit refs in review task text updated (pre-rebase dangling → ab51c2e..ff68762)
2026-08-12 16:42:16 +03:00
e89240fbf9 meta(tasks): create [sovereign-catalog-wave2-review] in OpeItcLoc03/skills 2026-08-12 13:02:00 +00:00
f8a6709545 meta(tasks): close [context7-cli-skill] in OpeItcLoc03/skills 2026-08-12 10:21:41 +00:00
8e2b260b6b meta(tasks): close [skill-frontmatter-lint] in OpeItcLoc03/skills 2026-08-12 10:20:25 +00:00
b9f948a670 meta(tasks): close [rename-repo-to-skills] in OpeItcLoc03/skills 2026-08-12 10:18:13 +00:00
cf8a14e441 meta(tasks): create [agent-neutral-skill-pipeline] in OpeItcLoc03/claude-skills 2026-08-12 09:58:09 +00:00
ea1b4a4f37 meta(tasks): create [skill-frontmatter-lint] in OpeItcLoc03/claude-skills 2026-08-12 09:58:04 +00:00
122a82c046 meta(tasks): create [rename-repo-to-skills] in OpeItcLoc03/claude-skills 2026-08-12 09:57:59 +00:00
c99ab74911 meta(tasks): create [context7-cli-skill] in OpeItcLoc03/claude-skills 2026-08-12 09:57:48 +00:00
07e782040d fix(session-inbox-monitor): scope pi extension to own project inbox only
Per vitya's rule an agent may only read its own directory's inbox. The
first global-scan version (all ~/projects inboxes + PI_INBOX_ROOTS) was
scrapped same day; rewrote as session-scoped: watches only
<ctx.cwd>/.claude-inbox/, decoy test proves other inboxes untouched.
2026-08-10 22:49:53 +03:00
a0491e00fd feat(session-inbox-monitor): pi support — global extension section, v0.3.0
Pi (pi-coding-agent) sessions get inbox delivery via global extension
(.common/lib/pi-extensions/inbox-monitor.ts → ~/.pi/agent/extensions/).
Not cwd-scoped: any .claude-inbox/ message pages the current session with
project name in header. Headless = no delivery. SKILL.md v0.2.2→v0.3.0.
2026-08-10 22:43:18 +03:00
caf99cb251 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 10:10:01 +00:00
ac6b4f6a9a meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:22572 2026-06-18 10:06:22 +00:00
d775f31f0d chore(tasks): re-ready windows-fixes after proxy fix (clear stale claim)
The first autonomous run blocked exit 1 because the service-spawned
claude bypassed the user proxy (xray :10808) and hit a geo-block.
Proxy env now injected into the runner service. Flip 🔵, drop the
stale Owner/Claim stamp so the poller re-claims and retries.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 13:05:52 +03:00
690f339991 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:31:24 +00:00
cc729cb590 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:27:39 +00:00
6bc8f78282 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:25:23 +00:00
6ad2ff9c49 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:25:21 +00:00
9ce8b23c2b meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:15:25 +00:00
46e474bf29 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:15:24 +00:00
8492ffbfc8 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:14:25 +00:00
1f5c488b00 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:14:24 +00:00
0ac91db75d meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:13:25 +00:00
2c405687b5 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:13:24 +00:00
0fd8b9cd2a meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:12:25 +00:00
c1c42d63f3 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:12:24 +00:00
5b16a7a3f3 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:10:33 +00:00
1c9647e7a1 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:10:32 +00:00
a82e974595 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:09:33 +00:00
3a73b967eb meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:09:32 +00:00
260383b8b5 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:08:32 +00:00
d83119bcb0 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:08:32 +00:00
f0bb8be811 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 09:07:33 +00:00
8796a6edb3 meta(tasks): claim [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills by DESKTOP-NSEF0UK:claude-opus:12744 2026-06-18 09:07:32 +00:00
22bf99df21 fix(tasks): drop stray lowercase weight/notify on windows-fixes task
tasks_create emitted lowercase **weight:**/**notify:** body prose; the
later capital **Weight:** needs-claude coexisted with the stale
lowercase **weight:** needs-human, and the poller parsed needs-human
(case-insensitive, last wins) -> task skipped. Remove the lowercase
dupes; only **Weight:** needs-claude + **Notify:** remain. (This is
exactly the gap tracked by [tasks-create-emit-weight-notify-fields].)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 12:06:40 +03:00
5dfebb07e8 chore(tasks): opt board in + scope autonomous duty to one task
Add L1 **Poller:** eligible marker; ensure every ready task except
setup-agents-task-runner-windows-fixes carries **Weight:** needs-human
so the armed poller claims only that one task (no churn).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 11:42:38 +03:00
cf8d247250 meta(tasks): update [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 08:26:55 +00:00
f66f5a50b2 meta(tasks): create [setup-agents-task-runner-windows-fixes] in OpeItcLoc03/claude-skills 2026-06-18 08:12:28 +00:00
a55f080613 meta(tasks): close meta-host-routing-hermes-mapping (mapped pending, build green)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 12:14:49 +03:00
8205f5d758 fix(session-inbox-monitor): UTF-8 OutputEncoding forward-guard in SessionStart hook (v0.2.2)
Closes session-inbox-monitor-encoding-guard-followup (finding from -review
structural audit item E, CONCERN).

inbox-monitor.ps1 emitted ConvertTo-Json (incl. the interpolated inbox path)
to a redirected pipe under WinPS 5.1 without setting [Console]::OutputEncoding
— the same context that mojibaked stop-dispatcher. ASCII-safe today, but the
inbox path is user-data, so a non-ASCII path/content would mangle the inject.

- Add [Console]::OutputEncoding + $OutputEncoding = UTF8 after the $ProjectDir
  gate (mirror of stop-dispatcher.ps1). Comment text kept pure ASCII.
- Regression under WinPS 5.1: parse 0 errors; ran hook against a Cyrillic-path
  project, read raw stdout bytes as no-BOM UTF-8 -> JSON valid, Cyrillic path
  round-trips intact.
- Re-deployed to ~/.claude/hooks/inbox-monitor.ps1, SHA256 byte-identical.
- SKILL.md Mojibake failure-mode extended; version 0.2.1 -> 0.2.2 (PATCH).

install/hermes/dist not rebuilt — PATCH needs only reload-plugins; the runtime
hook is deployed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 12:05:15 +03:00
c5f983a2a2 meta(tasks): close review-kit — 3 tracks VERDICT PASS
Clean non-implementer session: did not install/modify the skill, hook, or
SKILL.md; trigger checks + structural audit delegated to clean-context
unprimed subagents.

- inter-session-peer-discipline-test-trigger: pos 4/4 -> peer (high),
  0 false-positive across 5 foreign phrases (3 monitor-raise + 2 multi-machine
  backend), RU+EN.
- inter-session-peer-discipline-review: body v0.1.1 carries all 3 principles
  (proposal-not-authority / human-ratification-gate / echo-chamber-guard);
  complements global CLAUDE.md inter-session-messaging, no blocking findings.
- session-inbox-monitor-review (umbrella): activation 3/3 monitor + neg clean
  (X2 RU-backend low-conf observation); structural hook audit 5 PASS / 1 CONCERN
  (A sweep, B inject-one+headless, C no-loop, D body<->reality, E encoding latent);
  received-msg-fp counted RESOLVED via (b); hermes kept pending until tool-side audit.

Filed follow-up: session-inbox-monitor-encoding-guard-followup
(latent UTF-8 OutputEncoding guard missing in inbox-monitor.ps1).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 12:00:23 +03:00
38ac9ef5d1 feat(hermes): map inter-session-peer-discipline as pending + file its ledger
Un-reds the hermes build (build fails on unmapped skills in skills/; this skill
landed in sources 2026-06-16 unmapped). Entry is mode:pending, intended auto/meta
— a purely behavioral governance skill (no tool-side effects) that should pass a
non-implementer test-trigger + review before auto-firing. Filed 
inter-session-peer-discipline-test-trigger + 🔵 -review.

Zone confirmed claude-skills (skill lives in this repo). Human-ratified; workshop
coordinated as a peer proposal, not authority (per the skill itself). YAML validated
(33 skills, 9 pending). Schema version untouched.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 11:45:42 +03:00