# Review Loop

> - Review an explicit plan/code/PR SHA delta with a risk-scaled panel, fix one complete finding batch, validate the changed delta, and emit a durable review receipt. Defaults to one reviewer, adds targeted lenses for sensitive work, caps normal finding-bearing rounds, and avoids re-reading already certified branch history. Only invoke as $review-loop / /review-loop, or when a delivery skill calls it. Works identically under Codex and Claude Code.

## Facts
- Page: https://tashan.sh/capability/skill-comment-io-review-loop
- tashan id: skill:comment-io/review-loop
- Source: https://github.com/comment-io/claude-code-plugin
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 80.0
- Freshness: 95.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r review-loop ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-09 by tashan (https://tashan.sh) from public evidence. Scorer s5.