Codex Plugin Cc
Run OpenAI Codex code reviews and delegate bug investigations as background jobs without leaving Claude Code.
Overview
Codex Plugin CC is an agent skill most often used in Ship (also Build, Operate) that runs OpenAI Codex reviews and background delegated tasks from inside Claude Code.
Install
npx skills add https://github.com/aradotso/trending-skills --skill codex-plugin-ccWhat is this skill?
- Seven slash commands: review, adversarial-review, rescue, status, result, cancel, and setup
- Standard read-only Codex review on uncommitted changes or branch diffs
- Steerable adversarial review that challenges design decisions and assumptions
- Background delegation via rescue with status, result (session ID for codex resume), and cancel
- Setup verifies Codex install, auth, and optional review-gate enablement
- Seven documented slash commands for review, delegation, and job control
- Background jobs expose Codex session IDs for codex resume
Adoption & trust: 708 installs on skills.sh; 31 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want Codex-quality review and async investigation in the same Claude Code loop without manually copying diffs into another terminal.
Who is it for?
Claude Code users who already authenticate Codex and want parallel review plus delegated fix/investigation jobs with job tracking.
Skip if: Builders not using Claude Code or Codex, or teams that need MCP-only tooling with no OpenAI Codex account.
When should I use this skill?
User asks to review code with Codex, run adversarial review, delegate a task to Codex, investigate a bug via Codex, set up the plugin, or check background job status.
What do I get? / Deliverables
You invoke slash commands for review, adversarial critique, or background rescue and retrieve structured Codex output with session IDs to resume work.
- Codex review or adversarial review report on diffs
- Background job output retrievable via result command
- Verified setup and optional review-gate configuration
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Ship because the headline workflows are read-only reviews, adversarial design challenges, and optional review gates before changes land. Subphase review matches `/codex:review`, `/codex:adversarial-review`, and setup of the review gate—not generic backend coding.
Where it fits
Run `/codex:review` on your branch diff before opening a PR to a solo side project.
Use `/codex:adversarial-review` when you want assumptions and tradeoffs challenged on a refactor plan.
Delegate a gnarly integration bug to `/codex:rescue` while you keep implementing the next feature.
Pull finished investigation output with `/codex:result` and resume the Codex session to apply a minimal fix.
How it compares
Agent-plugin orchestration between Claude Code and Codex—not a standalone MCP security auditor or generic chat review prompt.
Common Questions / FAQ
Who is codex-plugin-cc for?
Solo and indie developers shipping with Claude Code who want OpenAI Codex for second-opinion reviews and background subagent tasks from one session.
When should I use codex-plugin-cc?
During Ship for diff reviews and adversarial design checks; during Build or Operate when you delegate bug hunts or fixes with `/codex:rescue` and poll `/codex:status`.
Is codex-plugin-cc safe to install?
Review the Security Audits panel on this Prism page and confirm Codex and Node dependencies match your org policy before enabling review gates or background jobs.
SKILL.md
READMESKILL.md - Codex Plugin Cc
# Codex Plugin for Claude Code > Skill by [ara.so](https://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 for `codex 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 ```bash /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /reload-plugins ``` ### 2. Verify setup ```bash /codex:setup ``` If Codex CLI is missing, `/codex:setup` can install it for you via npm, or install manually: ```bash npm install -g @openai/codex ``` ### 3. Authenticate with Codex ```bash !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. ```bash # 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. ```bash # 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. ```bash # 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: ```text Ask Codex to redesign the database connection to be more resilient. ``` ### `/codex:status