Concept page (2026-04-28) still documented the plugin context7@claude-plugins-official as single source — stale vs setup-context7 v2.0.0 CLI-first migration (2026-08-12). Rewrote: CLI + key in ~/.config/projects-secrets/ctx7.env as canonical, plugin era demoted to rollback-only, whoami!=key-check gotcha recorded. Index entry + log updated. Surface: review finding on session-ritual-context7-pins-review (already closed VERDICT PASS).
RISK-2 drift fix: 'Не построен — follow-up' → points at the deployed extension
(.common/lib/pi-extensions/session-close-ritual.ts), records why agent_end not
agent_settled (live-verified), bump 0.4.0→0.5.0 (MINOR), dist rebuilt.
51 🟢 blocks (2026-05..2026-08 done + sovereign-catalog-wave2-review close) moved off the
board to keep it lean, per using-tasks archival rule (threshold ≥10 exceeded ~5x).
Repo convention .tasks/.archive/done-YYYY-MM.md (matches existing done-2026-05.md).
Reviewer findings (sovereign-catalog-wave2-review, inbox 2026-08-12T13:30Z):
F1 dist/project-discipline.skill was stale (0.1.2 vs 0.2.0) — rebuilt, now 0.2.1.
F2 description contradiction — leftover old Rule-4 text («grant via разреши
автопуш…» + duplicate (5)) survived my v0.2.0 edit; removed, kept the
'Activated by' activation line. Body Rule 4: dropped stale 'any grant' /
'the grant does not apply' references (no grant concept in free-push rule).
lint 0/0.
Operator correction (2026-08-12): the ask-before-push ban accidentally became
global; the real gate belongs only to books (push to master = Gitea Actions
auto-deploy). New Rule 4: ordinary fast-forward push needs no confirmation by
default; a project with a local push-gate skill (convention push-gate, e.g.
books) overrides this in that project; force/delete/non-ff/other-remote always
ask. books/.claude/skills/push-gate + books/.agents/skills/push-gate carry the
old gate semantics (per-session grant / manual ask / session reset / summary
commit for Gitea Actions table).
RED (2026-08-12, clean pi -p subprocesses): user phrases «прогриль мой план»,
«grill my plan», «хватит, точи план», «прогриль с доками» all resolved to
grilling, NOT grill-me/grill-with-docs. Root cause (verified in pi docs
skills.md): disable-model-invocation: true hides a skill from the system
prompt — the thin user-wrapper split (mattpocock's slash-command model) is
structurally unreachable in pi's natural-language matching.
GREEN: single grilling v0.2.0 with integrated Docs mode (trigger «с доками» /
«зафиксируй» → decision record to .wiki/concepts/<topic>-decision.md or
.brainstorm/ append). Re-run: 5/5 positive → grilling, 4/4 negative clean.
Removed grill-me + grill-with-docs (invisible in pi, dead weight); README
table updated; lint 0/0; ~/.claude/skills = 39; dist pruned+rebuilt.
Convergent phase of the brainstorm flow: user says «хватит, к промоушену» →
grill session (design tree, rounds, frontier, numbered Q's with recommended
answers) → decision record. Adaptations to our conventions:
- grill-with-docs writes .wiki/concepts/<topic>-decision.md (project-discipline
Rule 1) or appends to .brainstorm/ running record in the workshop zone
- grilling sub-agent line made cross-agent honest (look up facts directly
when no subagent spawning)
- disable-model-invocation: true on both user wrappers
Provenance pinned to real commit 84fdeffd (not TBD). README table updated.
lint: 0/0; ~/.claude/skills now 41.
Override semantics kept generic: response style wins over multiple-choice
defaults; no dead plugin references left in live skill bodies (0 refs).
Version stays 0.1.1 (same commit family, text-only).
