# Code Review

> Review a finished change against its plan. Spawns 1 reviewer subagent, reports ship/rework with severity-tagged findings. Use AFTER /code-build.

- Skill: `alexeyshishin/code-review` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add alexeyshishin/code-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/alexeyshishin/code-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: alexeyshishin (https://skillmd.com/u/alexeyshishin)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/alexeyshishin/code-review

---


# Skill: /code-review

ORCHESTRATOR. One reviewer subagent. Read-only — the reviewer does not fix.

## Invocation
`/code-review <slug>`

## Steps
1. **Gather**: plan `swarm-report/<slug>-plan.md` + build report `swarm-report/<slug>-build.md`
   + the diff (`git diff` for staged + unstaged, or vs the branch point).
2. **Spawn 1 reviewer** (`Task`, `general-purpose`). Prompt:
   > Answer TERSE. Read `.claude/agents/reviewer.md` and follow it exactly.
   > Plan: swarm-report/<slug>-plan.md
   > Diff below:
   > <paste git diff here>

   Paste the diff INTO the prompt — the reviewer must not re-read the whole repo.
3. **Report** the reviewer's verdict + findings verbatim.
4. If `verdict: rework` — the findings ARE the input to a `/code-build <slug>` retry. Do not
   auto-fix here; hand them back and let the user decide.