maintainer-preflightlisted

# Maintainer preflight (claude-grok-build-plugin) Run these before saying done. Evidence, not vibes. **And these gates are not the last step.** Step 8 of "작업 수행 방법" in root `CLAUDE.md` — post-execution verification plus an audit of the measurements that got you here — is mandatory and runs AFTER the PR merges. `CLAUDE.md` owns that rule; do not restate it here. The short of it: check `origin/main` content rather than the log, re-run the original reproduction against the shipped bundle, and re-derive every finding by a second independent method before acting on it. Measured 2026-09-12: in one audit the measurement harness was wrong 6 times against 2 real defects. **A code fix also needs a Grok second opinion before done** — the adversarial pass is step 5 of "작업 수행 방법" in root `CLAUDE.md`, which owns the recipe (a review prompt that asks only for prose never terminates). Read its `verdict.md` yourself, and verify any finding by measurement before acting on it. ## Always ```bash cd mcp-server npm ci # missing OR possibly-stale node_modules — see below npm test npm run typecheck ``` Both must pass. Report the real counts from this session's run — never summarize a run you did not execute. **`npm ci` is not only for a missing `node_modules`.** A tree that is merely *stale* is worse than a missing one, because the build succeeds and silently ships the wrong dependency. Measured 2026-08-09: `node_modules` held `fast-uri` 3.1.4 while the lockfile pinned 3.1.5, and `np