Commit graph

3 commits

Author SHA1 Message Date
8d1ef43801 fix(linkedin-studio): S25 harden measure — explicit Glob, drop Read from routing front-door
measure is the Measure-journey routing front-door (v4.1): guided "how am I
doing?" -> routes to the analytics command that owns the work; delegates only,
never crunches numbers. Routing axis is clean — all 5 emitted targets
(import/report/analyze/audit/ab-test) resolve to commands/Y.md. Delegates-only
holds: the 3 crunch/analysis mentions (:7/:20/:40) are all no-do promises, no
leak.

Grant-hygiene was the one finding, and it differs from S24 create. There Glob
was a pure orphan (no filesystem check at all). Here measure HAS an optional
Step 0 ("if .../analytics/ holds imported data, note last import") that gives
Glob a real home — but the grant<->use link was implicit (body named no tool),
and Read hung on the same vague Step 0. Operator chose: make Glob explicit,
drop Read as redundant (the import-date need is met by a Glob listing).

2 edits, commands/measure.md only:
- allowed-tools :11: drop Read; net = {Glob, AskUserQuestion}.
- Step 0 :23: "You may Glob .../analytics/; if it holds imported data, note last
  import" — gives the retained Glob grant a named body home.

Verify: re-grep final — Read as tool name NONE, allowed-tools = Glob +
AskUserQuestion (:11-12), Glob now in body :23; routing unchanged (5/5);
git diff --stat = 1 file +1/-2; test-runner 81/0/0 exit 0; counts 29/19
unchanged (.md-only). FIXED, 0 deferrals. Scope note: Glob-orphan question now
resolved for measure (it had a home via Step 0; create did not); linkedin (S26)
still to check independently.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016qgzo6rxthw7KuxHjn5vyE
2026-06-19 21:38:02 +02:00
6bd263144f docs(linkedin-studio): M0-15 — repoint remaining prose families + route ab-tests/plans 2026-06-18 13:04:18 +02:00
52df229dfc feat(linkedin-studio): S14 — journey layer (create/measure front-doors + 5-journey router), v4.1.0
14a's cold command-rationalization found ZERO redundancy across the 27 commands
(no defensible merge/cut), so the operator reframed S14 from "merge/cut" to
"add a journey layer over the kept atomics".

- Add /linkedin:create + /linkedin:measure — delegate-only guided front-doors
  (Read/Glob/AskUserQuestion only; route to the command that owns the work)
- Re-tier commands/linkedin.md into 5 journeys (Start/Create/Engage/Measure/Grow);
  onboarding/strategy elevated as Start/Grow front-doors; Engage = calendar+firsthour tier
- 14a honesty nits: router now lists firsthour; calendar cross-links to firsthour;
  competitive confirmed UNGATED (the claimed 1K-gating inconsistency was unfounded)
- Lockstep: EXPECT_COMMANDS 27->29, v4.0.0->4.1.0 across plugin.json / README badges /
  plugin+root CLAUDE.md / README / CHANGELOG; new README commands-badge lint guard
- 14a deliverable corrected: multiplatform entry added (26/27 -> 27/27), header counts,
  competitive nit withdrawn
- Independent /trekreview (2 Opus reviewers) raised 3 MAJORs (stale commands badge,
  router competitive self-contradiction, STATE.md count) — ALL remediated in-session;
  verdict ALLOW

Gate: test-runner.sh 74/0/0; node --test 98/98; commands=29; v4.1.0 consistent.
Additive/minor — no command removed/renamed/behavior-changed; reload registers create+measure.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 21:27:06 +02:00