rig-reviewlisted
Install: claude install-skill agent-rig/rig
# rig-review — find and fix, in one skill
Local code review with two verbs:
- **`find`** (default) — walk the project's `REVIEWER.md` catalog **and** the
applicable per-scope invariants against a diff with a fresh-context `reviewer`
agent (two passes), and return a triaged P0–P3 finding list. **Read-only** —
it reports, it doesn't edit.
- **`fix`** — take review feedback and loop a `coder` agent over it until the
review comes back clean (or a round budget is hit). Two feedback sources: a PR
**review bot** on an open PR, or **local** `find` results.
The point is to **pre-empt the PR review bot**: every finding caught and fixed
locally is one you don't pay PR round-trip latency on. Implement/epic-style
flows call `rig-review find` then `rig-review fix --source local` so the loop
lives in one place.
## Configuration
Reads `.rig/config.json`:
- `review.patternsFile` — the P0–P3 catalog the reviewer walks (default
`.claude/REVIEWER.md`). If absent, fall back to the kit's generic categories
(correctness, security/trust-boundary, error-handling, concurrency,
API/contract, tests, style) and say so.
- `review.bot` — PR review bot to poll/re-trigger: `codex`, `claude`, or `none`
(default `none`). **`none` forces the local-only loop** for `fix`.
- `review.botRetrigger` — comment that re-triggers the bot (e.g. `@codex
review`). Required when `bot` is not `none`.
- `review.maxRounds` — max fix↔recheck rounds before handing to a human
(default `5`); `--rounds N`