codex-plugin-cc
Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.
- Installs
- 839
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/reason-machines/trending-skills --skill codex-plugin-cc- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads codex-plugin-cc automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Codex Plugin for Claude Code
Skill by ara.so — Daily 2026 Skills collection.
A Claude Code plugin that lets you run OpenAI Codex code reviews and delegate background tasks to Codex directly from your Claude Code session. Use it for read-only code reviews, adversarial design challenges, and handing off investigative or fix tasks to Codex as a subagent.
What It Does
/codex:review— Standard read-only Codex code review of uncommitted changes or a branch diff/codex:adversarial-review— Steerable review that challenges design decisions, tradeoffs, and assumptions/codex:rescue— Delegate a task (bug investigation, fix, etc.) to Codex as a background subagent/codex:status— Check progress of background Codex jobs/codex:result— Retrieve output from a finished job (includes Codex session ID forcodex resume)/codex:cancel— Cancel an active background job/codex:setup— Verify Codex is installed and authenticated; optionally enable/disable the review gate
Requirements
- Node.js 18.18 or later
- A ChatGPT subscription (Free tier works) or an OpenAI API key
- Claude Code with plugin support
Installation
1. Add the marketplace and install the plugin
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
2. Verify setup
/codex:setup
If Codex CLI is missing, /codex:setup can install it for you via npm, or install manually:
npm install -g @openai/codex
3. Authenticate with Codex
!codex login
Supports ChatGPT account login or API key. Your existing Codex CLI authentication is reused automatically if already logged in.
Key Commands
/codex:review
Runs a standard read-only Codex review on your current work.
# Review uncommitted changes
/codex:review
# Review diff against a base branch
/codex:review --base main
# Run in the background (recommended for multi-file changes)
/codex:review --background
# Run and wait inline
/codex:review --wait
/codex:adversarial-review
Challenges implementation decisions, tradeoffs, and hidden assumptions. Accepts optional free-text focus after flags.
# Basic adversarial review
/codex:adversarial-review
# Target a branch diff with a specific focus
/codex:adversarial-review --base main challenge whether this caching approach was correct
# Run in background, focus on race conditions
/codex:adversarial-review --background look for race conditions and question the retry design
/codex:rescue
Hands off a task to Codex via the codex:codex-rescue subagent.
# Investigate a failing test
/codex:rescue investigate why the tests started failing
# Apply a minimal fix
/codex:rescue fix the failing test with the smallest safe patch
# Resume the most recent Codex session for this repo
/codex:rescue --resume apply the top fix from the last run
# Start fresh (ignore previous session)
/codex:rescue --fresh investigate the regression
# Use a specific model and effort level
/codex:rescue --model gpt-5.4-mini --effort medium investigate the flaky integration test
# Use the faster "spark" model (maps to gpt-5.3-codex-spark)
/codex:rescue --model spark fix the issue quickly
# Run in the background
/codex:rescue --background investigate why the build is failing in CI
You can also trigger rescue via natural language to Claude:
Ask Codex to redesign the database connection to be more resilient.
/codex:status
# List all running and recent jobs for this repo
/codex:status
# Check a specific job
/codex:status task-abc123
/codex:result
# Get result of the most recent finished job
/codex:result
# Get result for a specific job
/codex:result task-abc123
Output includes a Codex session ID. Resume that session directly in Codex:
codex resume <session-id>
/codex:cancel
# Cancel the most recent active job
/codex:cancel
# Cancel a specific job
/codex:cancel task-abc123
/codex:setup — Review Gate
# Enable the stop hook review gate
/codex:setup --enable-review-gate
# Disable it
/codex:setup --disable-review-gate
Warning: The review gate runs a Codex review on every Claude response and blocks the stop if issues are found. This can trigger long Claude/Codex loops and drain usage limits. Only enable it when actively monitoring the session.
Configuration
The plugin uses the same config.toml as the Codex CLI. Configuration is layered:
| Location | Scope |
|---|---|
~/.codex/config.toml | User-level defaults |
.codex/config.toml (project root) | Project-level overrides (requires trusted project) |
Example: Set default model and effort for a project
# .codex/config.toml
model = "gpt-5.4-mini"
model_reasoning_effort = "xhigh"
Example: Point to a custom OpenAI-compatible endpoint
# ~/.codex/config.toml
openai_base_url = "https://your-custom-endpoint.example.com/v1"
API keys and authentication are managed via codex login — do not hardcode keys in config files. The CLI reads from the authenticated session or from the OPENAI_API_KEY environment variable.
Common Patterns
Review before shipping
/codex:review --base main
Start a long-running review, check back later
/codex:adversarial-review --background look for auth and data-loss risks
/codex:status
/codex:result
Delegate a bug investigation and resume in Codex
/codex:rescue --background investigate why the integration test is flaky
# ... later ...
/codex:result
# Copy session ID from output, then:
codex resume <session-id>
Iterative rescue workflow
# First pass
/codex:rescue investigate the failing build
# Apply what Codex found, continuing the same thread
/codex:rescue --resume apply the recommended fix from the last run
# Start completely fresh
/codex:rescue --fresh re-investigate with a clean slate
Use Claude to delegate naturally
Ask Codex to refactor the authentication module to remove the global state.
Claude will invoke the codex:codex-rescue subagent automatically.
Troubleshooting
/codex:setup says Codex is not installed
npm install -g @openai/codex
# or let /codex:setup install it for you
Codex is installed but not authenticated
!codex login
Supports ChatGPT account or API key. If using an API key directly:
export OPENAI_API_KEY=your-key-here
Background job seems stuck
/codex:status
/codex:cancel task-abc123
Plugin commands not appearing after install
/reload-plugins
Project-level config not being picked up
Project config in .codex/config.toml only loads when the project is trusted by Codex. Run codex directly in the project directory to trust it, or check the Codex advanced config docs.
Review gate creating runaway loops
Disable it immediately:
/codex:setup --disable-review-gate
How It Works Internally
- The plugin wraps the local
codexbinary and the Codex app server - All jobs run in your local environment against your local repository checkout
- Authentication, config, and model settings come from your existing Codex CLI setup
- Background jobs are tracked per-repository and can be resumed in Codex directly via session IDs
- The
codex:codex-rescuesubagent is registered in/agentsand can be invoked by Claude automatically when you ask it to delegate work to Codex
FAQ
What does the codex-plugin-cc skill do?
Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.
How do I install codex-plugin-cc?
Run npx skills add https://github.com/reason-machines/trending-skills --skill codex-plugin-cc in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/codex-plugin-cc/ (personal) or .claude/skills/codex-plugin-cc/ (project).
Which AI agents can use codex-plugin-cc?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is codex-plugin-cc safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains codex-plugin-cc?
It is published by reason-machines in reason-machines/trending-skills. It has 839 recorded installs.
More from reason-machines/trending-skills
openclaw-control-center
reason-machines/trending-skills
Local-first, security-first control center for OpenClaw agents — visibility dashboard with readonly defaults, token attribution, collaboration tracing, and safe write operations.
inkos-multi-agent-novel-writing
reason-machines/trending-skills
Multi-agent CLI system for autonomous novel writing, auditing, and revision with human review gates
claude-hud-statusline
reason-machines/trending-skills
A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.
understand-anything-knowledge-graph
reason-machines/trending-skills
Turn any codebase into an interactive knowledge graph using Claude Code skills — explore, search, and ask questions about any project visually.
agency-agents-ai-specialists
reason-machines/trending-skills
A collection of specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, and other AI coding tools — covering engineering, design, marketing, sales, and more.
agent-browser-automation
reason-machines/trending-skills
Headless browser automation CLI for AI agents using native Rust binary with Chrome DevTools Protocol
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available