# codex-plugin-cc

Runs OpenAI Codex reviews and delegates background fixes directly from Claude Code. Good for getting an outside critique on diffs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 838 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/codex-plugin-cc/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/codex-plugin-cc

## What it does

This skill ties Claude Code to the Codex command line. Running `/codex:review` evaluates uncommitted files or branch diffs against another branch. The `/codex:adversarial-review` command takes a different path. It actively questions design choices and highlights hidden assumptions.

Heavy lifting can move to the background through `/codex:rescue`. This delegates investigations or bug fixes to a separate Codex subagent. You check progress with `/codex:status` and pull logs using `/codex:result`. Outputs include a session identifier. Work can resume inside the standalone Codex CLI at any point.

Prerequisites include Node.js 18.18 or newer alongside an authenticated `@openai/codex` CLI package. Project settings reside in `.codex/config.toml`. Turning on the optional review gate blocks agent stops on unresolved issues, which risks triggering recursive loops and depleting rate limits.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill codex-plugin-cc -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/codex-plugin-cc/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/codex-plugin-cc/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill codex-plugin-cc -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/codex-plugin-cc/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill codex-plugin-cc -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/codex-plugin-cc/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills codex-plugin-cc
```

2. **Manually: put the files in place**
- File: `.github/skills/codex-plugin-cc/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill codex-plugin-cc -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/codex-plugin-cc
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/codex-plugin-cc/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill codex-plugin-cc -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/codex-plugin-cc/SKILL.md

## When to use it
- audit uncommitted changes against a base branch
- challenge architecture tradeoffs through adversarial review
- delegate flaky test investigations to a background subagent
- retrieve session identifiers to continue troubleshooting in Codex CLI

## Example prompts
- /codex:review --base main
- /codex:adversarial-review --background challenge the caching strategy and retry design
- /codex:rescue investigate why integration tests fail

## Similar
- [oracle](https://affpapa.org/en/nevibecode/skills/oracle.md) — skill · 5200 installs
- [codex](https://affpapa.org/en/nevibecode/skills/giuseppe-trisciuoglio-codex.md) — skill · 3400 installs
- [codex-skill](https://affpapa.org/en/nevibecode/skills/codex-skill.md) — skill · 408 installs
- [codex-review](https://affpapa.org/en/nevibecode/skills/alinaqi-codex-review.md) — skill · 328 installs
- [gpt-image-2](https://affpapa.org/en/nevibecode/skills/gpt-image-2.md) — skill · 84300 installs
- [gpt-image](https://affpapa.org/en/nevibecode/skills/gpt-image.md) — skill · 12300 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 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