# code-review-swarm

code-review-swarm deploys coordinated AI review agents against pull requests via the GitHub CLI. It flags security flaws and architecture drift before merging.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/github/code-review-swarm.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/code-review-swarm

## What it does

This subagent orchestrates focused review roles across code diffs pulled directly through `gh`. Instead of relying solely on linters, it triggers `npx ruv-swarm` to evaluate security risks and code structure. Critical findings can directly block the pull request.

A working GitHub CLI session is mandatory. The pre-hook runs `gh auth status` and halts immediately if authentication is missing. Under the hood, it runs `Bash` commands and relies on `claude-flow` MCP tools to coordinate child agents. Thresholds and required checks are controlled by `.github/review-swarm.yml`.

## Requirements
- Works with: GitHub

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/code-review-swarm.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/code-review-swarm.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/code-review-swarm.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/github/code-review-swarm.md

## When to use it
- inspect pull requests for OWASP vulnerabilities and secret exposure
- detect inefficient database queries and memory allocation issues
- evaluate SOLID design patterns and module coupling
- post structured review comments directly to GitHub using `gh`

## Example prompts
- Run code-review-swarm on PR 123 and post the findings
- Perform a security review on PR 42 with suggested fixes
- Analyze architectural coupling and performance bottlenecks for this pull request

## Similar
- [gitnexus-pr-swarm-review](https://affpapa.org/en/nevibecode/skills/gitnexus-pr-swarm-review.md) — skill · 438 installs
- [review-swarm](https://affpapa.org/en/nevibecode/skills/review-swarm.md) — skill · 820 installs
- [swarm-pr-feedback](https://affpapa.org/en/nevibecode/skills/swarm-pr-feedback-2.md) — skill · ★ 539 repo stars
- [dyad:swarm-pr-review](https://affpapa.org/en/nevibecode/skills/dyadswarm-pr-review.md) — skill · ★ 22348 repo stars
- [codebase-review-swarm](https://affpapa.org/en/nevibecode/skills/codebase-review-swarm-2.md) — skill · ★ 539 repo stars
- [dyad:multi-pr-review](https://affpapa.org/en/nevibecode/skills/dyadmulti-pr-review.md) — skill · ★ 22348 repo stars

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
