← ClaudeAtlas

review-gateslisted

Default review gates for any of Sarah's projects — which review runs when, on which model, at what context cost. Use before every commit, when integrating a helper's lane, and when a batch of PLAN.md items is done. If the project has its own review-workflow skill, follow that too; it wins on conflict.
schen22/claude-config · ★ 0 · Code & Development · score 70
Install: claude install-skill schen22/claude-config
# Review gates Goal: quality at the lowest token cost. Reviews read diffs, not the codebase, and heavy output stays out of the orchestrator's context. ## Gate 0 — self-check before every commit (whoever commits) 1. While iterating: the project's fast gate (`npm run gate:fast` or equivalent). 2. Before the commit: the full gate (`npm run gate`). Only known failures allowed (listed in `PLAN.md`). 3. The project's constraints from its `CLAUDE.md`. 4. No raw logs, no screenshots. Helpers report in ≤ 15 lines (see `delegate`). ## Gate 1 — diff review, per lane or per own commit (orchestrator) 1. Read only `git diff <main>...lane/<name>` (or the staged diff) plus the helper's report. 2. Lens: does each commit do what its item says; stays in owned files; project constraints hold; each new test would fail before the change; no duplicate tests. 3. Verdict `SHIP` / `BLOCKED` + ≤ 5 one-line findings. 4. Blockers go back to the same helper via `SendMessage`. Should-fix → follow-up commit or a line in `PLAN.md` Next. 5. Risky task (JS behaviour, accessibility, security): one Sonnet reviewer helper, diff only, blockers only, ≤ 10 lines. ## Gate 2 — whole batch, once (Sonnet subagent) 1. One Sonnet helper runs the `review` skill over the batch diff. Blockers only, ≤ 10 lines. 2. Fix blockers only. No iterate-to-a-score loop; no expert panel unless Sarah asks. 3. Visual sign-off is Sarah's: point at the pages to open. 4. Update `PLAN.md` and Lessons. ## Models - Helpers