Address bot review on the Stop delivery path: the stop:evaluate-session
registration no longer carries async (an async Stop registration cannot
block), so delivery is synchronous, and the metadata fingerprint for the
changed entry is regenerated with the repo's own function; the delivery
marker is now claimed atomically with exclusive create and any write
failure fails closed instead of delivering without once-per-session
protection; the skill doc now marks the shell entry as counting-only,
requires the JavaScript evaluator through the plugin hooks for delivery,
and clarifies that Stop fires whenever Claude finishes responding; test
spawn helpers no longer coerce a failed spawn to exit 0.
Test plan:
- tests/hooks/evaluate-session.test.js: 25 passed, 0 failed (2 new:
marker write failure skips delivery, registration is synchronous);
pristine comparison: 22 passed, 3 failed (delivery, marker, registration)
- tests/hooks/hooks.test.js: 260 passed
- tests/hooks/stop-hooks-stdout.test.js: 48 passed
- tests/hooks/cursor-hook-dispatchers.test.js: 27 passed
- tests/integration/hooks.test.js: 27 passed
- scripts/ci/check-unicode-safety.js: passed
The v1 evaluator computed the learning signal but wrote it to stderr, which Claude Code never forwards to the model, so the learned-skills folder was never populated through this path.
Delivery now follows the maintainer-endorsed shape: an explicit stop_nudge_opt_in flag (default off, so existing installs are unchanged), the native Stop block contract (decision block plus reason) instead of plain stdout text, at most one delivery per session via a temp-dir marker, Stop-loop protection via stop_hook_active, and delivery only for sessions with a registered lease from SessionStart.
Tests: 7 new evaluator tests (opt-in off, no lease, one valid block then silence on repeat, stop_hook_active, short session, non-Stop event, missing session id). Evaluator suite 23/23 with the fix, failing on pristine; hooks suite 260/260; Stop stdout contract suite 48/48.
Limits stated plainly: end-to-end delivery in a live Claude Code session is not certified from this host (unit-level spawn plus parse only), and the fix ships inert by default until a user opts in.
- Migrate session-end.js and evaluate-session.js from CLAUDE_TRANSCRIPT_PATH
env var to stdin JSON transcript_path (correct hook input mechanism)
- Remove duplicate main() calls that ran before stdin was read, causing
session files to be created with empty data
- Add range validation (1-10000) on COMPACT_THRESHOLD in suggest-compact.js
to prevent negative or absurdly large thresholds
- Add integration/hooks.test.js to tests/run-all.js so CI runs all 97 tests
- Update evaluate-session.sh to parse transcript_path from stdin JSON
- Update hooks.test.js to pass transcript_path via stdin instead of env var
- Sync .cursor/ copies
- Wrap JSON.parse in try-catch for all 6 inline hooks in hooks.json
(dev-server blocker, tmux reminder, git-push reminder, doc blocker,
PR create logger, build analysis) — previously unguarded JSON.parse
would crash on empty/malformed stdin, preventing data passthrough
- Add config parse error logging to evaluate-session.js
- Fix plugin.schema.json: author can be string or {name,url} object,
add version (semver pattern), homepage, keywords, skills, agents
- Fix package-manager.schema.json: add setAt (date-time) field and
make packageManager required to match actual code behavior