An always-on agent-task-runner dry-run (2026-06-08) spuriously claimed/blocked 5
ready tasks via a runner workspace-divergence bug (poller API-claims to origin
raced the spawned agent's local-checkout pushes → git pull --ff-only failed →
tasks marked blocked, none actually worked). Restore all 5 to ⚪ ready:
using-yt-tools-rate-limit-guard, archive-roundtrip-test, skills-grouping-revisit,
hermes-converter-ci, tdd-criteria-precommit-hook.
yt-tools re-scoped: its target skills/using-yt-tools/SKILL.md is a deprecated
stub (v0.4.1); canonical content + referenced sections live in the
OpeItcLoc03/yt-tools plugin (v0.6.0). Rule still wanted — re-point at the plugin
repo, don't edit the stub. Agent's decision-trail (correct diagnosis) preserved
in the per-task file.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Don't-batch-YouTube-requests rule, filed from modulair-wiki ingest session
where ~21 rapid requests tripped HTTP 429 IP-block on both transcript-api and
yt-dlp. Captures empirical symptom + cooldown/one-at-a-time fix + en-US lang
gotcha, to land in SKILL.md as a What-NOT-to-do bullet + failure-mode row.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Second pass: filled the empty skeleton (When-to-use, Inputs, Steps, Failure
modes, Side effects, What-NOT) from the design archive
(.workshop/.archive/2026-05-29-skill-private-dev-public-publish.md). 0.1.0 -> 0.2.0.
Non-implementer subagent review found 3 findings, all fixed in this same increment:
- Step 5 dev->pub copy had no meta-exclusion -> would leak .wiki/.tasks/CLAUDE.md
into the PUBLIC fork. Added explicit meta-exclude + .gitignore backstop +
git-status check, plus a 4th failure mode for the leak.
- pub-folder origin was never established before Step 5 pushed to it -> Step 4 now
clones the GitHub fork into pub (origin=fork, upstream=canonical).
- Step 3 "same base" was unmechanized -> clone fork, add gitea remote, push base.
Closes review task: all findings filed and resolved; no follow-ups needed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Investigation finding: SRE module mismatch не воспроизводится на DESKTOP-NSEF0UK.
Three yt-dlp installs coexist:
- Python313\Scripts\yt-dlp.exe (system pip, first on PATH)
- ~\.local\bin\yt-dlp.exe (uv tool install, Python 3.14.3)
- ~\pipx\venvs\yt-tools\Scripts\yt-dlp.exe (pipx-bundled, Python 3.12.13)
All three return --version exit 0. All three interpreters import `re` cleanly.
yt-listen shims в ~/.local/bin и в pipx venv — byte-identical (SHA256 match).
Smoke-test diagnosis «uv-managed cpython-3.12 corrupt» вероятно misdiagnosis —
реальный виновник скорее всего был corrupt _sre.pyd в Python313 system install
(первый на PATH). uv с тех пор bumped 3.12 → 3.14.3, что независимо могло
залечить состояние. SKILL.md "Locating binaries" уже даёт корректный
fallback chain (PATH → ~/.local/bin → legacy venv); добавлять
\$HOME\pipx\venvs\yt-tools\Scripts приоритетным не нужно.
Closed wontfix без SKILL change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Symmetric to install-side --prune (e871c20). Removes
dist/<name>.skill files whose <name> is not in skills/*.
Design choices match install:
- Combined flag (build + prune in one run)
- Global scan, ignores -Names / positional filter
- Default off, print-and-delete, no confirmation
Bash wrinkle: when build.sh delegates to powershell.exe -File
build.ps1 (Windows-without-zip case), --prune is NOT forwarded.
Bash runs prune itself at the end of the script against the
shared dist/. Keeps the delegation surface narrow and the prune
logic single-sourced per shell.
[skip-tdd: wrapper] — same carve-out as install-side, smoke-test
evidence: fake dist/fake-stale-{sh,ps}.skill files created in real
dist/, ran build.{sh,ps1} --prune, verified fakes removed, real
caveman.skill etc. left intact.
Wiki .wiki/concepts/install-cross-platform.md extended:
- title broadened (Install → Install / Build)
- new "Build-side --prune" section
- scope note: dist-hermes/ is separate (managed by build-hermes.py)
Closes [install-ps1-build-prune-followup].
Closes 3/3 acceptance of [install-ps1]:
- (a) install.ps1 existed
- (b) --prune flag shipped in 6cf0e98
- (c) concept page now written
.wiki/concepts/install-cross-platform.md captures:
- why two scripts (PS for native-Win, sh for Linux/Mac)
- parity contract (shared invariants, flag-naming convention)
- --prune design choices and rejected alternatives
- scope boundary (install-side only; dist/.skill prune is separate)
Index + log updated per .wiki/CLAUDE.md schema.
STATUS.md: [install-ps1] ⚪ → 🟢, new ⚪ task
[install-ps1-build-prune-followup] filed for the analogous
flag on build.{sh,ps1}.
Empirical close: 1473-char description on using-vds-ops works
(7/7 smoke-test PASSED, listing shows full text, no fallback).
Memory note feedback_skill_description_length_limit.md was
paranoid — deleted from user memory (not in repo).
YAML colon-space gotcha memory kept (different concern, valid).
[using-synology-ops-disambiguation-uplift] ⚪ → 🟢
[using-synology-ops-review] ⚪ → 🟢
Reason: Synology NAS decommissioned permanently 2026-05-25.
Disambiguation between NAS and VDS for shared container names
(traefik etc.) is moot when only VDS exists. Review acceptance
criteria have no target — both the MCP endpoint and the host
fleet are gone.
Full skill retire (delete skills/using-synology-ops/, hermes
mapping entry, ~/.claude/skills/ install, MCP server registration,
dist-hermes rebuild) tracked as separate next-commit operation.
STATUS.md 1467 → 239 lines (-84%), 70 → 11 active blocks.
Archive: 21 → 57 done blocks (full snapshot, replaces prior partial).
Перемещено 36 done-блоков из STATUS.md в .archive/done-2026-05.md
(uses-yt-tools cluster, tdd-criteria rollout, bootstrap fixes,
session-handoff cluster, using-vds-ops/using-synology-ops promo,
interns-grep-audit, recommend-dont-menu, project-creation-lifecycle,
project-discipline-brainstorm-workspaces).
Один heading-emoji flip: [bootstrap-fix-tdd-recommend-template] ⚪ → 🟢
(ship-commit aac9088 2026-05-07 был авторитативным, ⚪ heading stale;
duplicate **Next action** spec block stripped at the same time).
[tasks-board-cleanup-2026-05] остаётся ⚪ в STATUS.md — по NB таски,
её закрытие идёт следующим batch'ем, не в этом же коммите.
Sliding overwrite после cluster milestone. Manual write по explicit user
direction — substantive-commit hook бы пропустил (предыдущий commit
2673efb prefix meta: в skip-list). Pattern «cluster-milestone regen» —
valid use case вне auto-trigger threshold.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
End-of-session write-mode invocation (trigger phrase "закрываем сессию").
Updates dogfood handoff with:
- self-referential commit 5f6e4e7 in Recent
- .admin push status (was pending → done)
- new Open трек row for unresolved dist-hermes drift
- guard against committing that drift without owner
Sliding contract — no .archive/handoff-*.md, history via git log.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First real session-handoff write-mode invocation — building the skill
and immediately eating own dogfood. Captures handoff for the session
that will pick up [session-handoff-test-trigger] (the last blocker for
[session-handoff-review]).
Sections per SKILL.md spec: Recent commits (8 local + 1 cross-repo),
Open треки (5), Спроси user'а (3), Не делать (5 preemptive guards),
Memory updates (3). Sliding overwrite — history via git log.
Validates:
- Read mode trigger-line discovery (CLAUDE.md now has it)
- Write mode composition (.tasks/STATUS.md + git log + decisions)
- Project-scope invariant (только cwd, никаких других mutations)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Previous commit 75d70f3 flipped the heading and _Updated_ but the body
edit silently fell through (multi-block replace miss). The block still
read "Status: ready / Where I stopped: (not started)" with the original
Path A/B next-action list — inconsistent with the 🟢 heading.
Filling the close-note now: 2 done (cwd + .admin/29724d41), 1 skip
(.workshop — workspace-contract format mismatch), 4 deferred (not on
this machine).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`(& git log -1 --format='%b')` in PowerShell collapses multi-line subprocess
output into string[]. The threshold check used `$body.Length` which on a
string[] returns the line count, not char count — so the body>200 condition
was effectively comparing "more than 200 lines", which is much harder to
meet. Files-count saves it in practice for big commits, but small-file
big-message commits were under-detected.
Fix: join the array back into a single string with `-join "`n"` before
measuring length. Verified via stdin-pipe smoke against current HEAD:
body chars now report 1255 (vs 29 before — the line count).
POSIX `.sh` variant unaffected — `$()` collapses output and `${#var}` is
char count.
Bump 0.3.0 → 0.3.1 PATCH (bugfix, no behavior contract change).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
