codex

Codex plugin for Claude Code

⚠️ Fork notice

This is a community fork of openai/codex-plugin-cc maintained at doubleDrake/codex-plugin-cc-supa. Tracked via Linear Project codex-plugin-cc-plus fork.

Planned differences from upstream (see Linear sub-issues SUP-365~377; current state: meta-only fork, no code changes yet):

• Broker idle timeout (10 min) — cc#108
• PID liveness check + crashed status auto-transition — cc#264/#164/#202/#222
• sendBrokerShutdown 5 s timeout — cc#245/#288 (PR#293 reference)
• A+ delegate command (/codex:delegate) — Codex=brain, Claude=hand pattern
• Stateful thread default — ephemeral: false
• /codex:consult command — cc#7
• --resume-id <threadId> flag — cc#230
• Auto-Context prefix rule in agents

See CHANGELOG.md for the running list.

Install (fork): /plugin marketplace add doubleDrake/codex-plugin-cc-supa then /plugin install codex@doubledrake-codex-supa.

Use Codex from inside Claude Code for code reviews or to delegate tasks to Codex.

This plugin is for Claude Code users who want an easy way to start using Codex from the workflow they already have.

What You Get

• /codex:do <natural-language request> — single entry point. Claude classifies the request and dispatches to the right sub-action. (Originally proposed as bare /codex but Claude Code's plugin namespace forces the /<plugin>:<command> form.) Examples:
  • /codex:do 인증 미들웨어 JWT로 리팩터해줘 → delegate
  • /codex:do 이 PR 리뷰해줘 → review
  • /codex:do 이 디자인 어떻게 생각해? → consult
  • /codex:do 좀비 잡 있어? → status
  • Use --as <action> for explicit override; ambiguous prompts trigger one AskUserQuestion.
• /codex:review for a normal read-only Codex review
• /codex:adversarial-review for a steerable challenge review
• /codex:delegate for a multi-step A+ delegation (Codex=brain, Claude=hand) — fork-original; the STATUS loop can also run as a Workflow (workflows/codex-delegate.js) for parallel, git-worktree-isolated delegations, while --pane stays for an interactive live teammate
• /codex:consult for design discussions / Q&A with persistent per-workspace thread — fork-original
• /codex:rescue, /codex:status, /codex:result, and /codex:cancel to delegate work and manage background jobs

All ten commands are first-class; /codex:do is just a router on top of the nine specific ones (INV-1: direct aliases keep working).

Requirements

• ChatGPT subscription (incl. Free) or OpenAI API key.
  • Usage will contribute to your Codex usage limits. Learn more.
• Node.js 18.18 or later

Install

Add the marketplace in Claude Code:

/plugin marketplace add openai/codex-plugin-cc

Install the plugin:

/plugin install codex@openai-codex

Reload plugins:

/reload-plugins

Then run:

/codex:setup

/codex:setup will tell you whether Codex is ready. If Codex is missing and npm is available, it can offer to install Codex for you.

If you prefer to install Codex yourself, use:

npm install -g @openai/codex

If Codex is installed but not logged in yet, run:

!codex login

After install, you should see:

• the slash commands listed below
• the codex:codex-rescue subagent in /agents

One simple first run is:

/codex:review --background
/codex:status
/codex:result

Usage

/codex:review

Runs a normal Codex review on your current work. It gives you the same quality of code review as running /review inside Codex directly.

[!NOTE] Code review especially for multi-file changes might take a while. It's generally recommended to run it in the background.

Use it when you want:

• a review of your current uncommitted changes
• a review of your branch compared to a base branch like main

Use --base <ref> for branch review. It also supports --wait and --background. It is not steerable and does not take custom focus text. Use /codex:adversarial-review when you want to challenge a specific decision or risk area.

Examples:

/codex:review
/codex:review --base main
/codex:review --background

This command is read-only and will not perform any changes. When run in the background you can use /codex:status to check on the progress and /codex:cancel to cancel the ongoing task.

/codex:adversarial-review

Runs a steerable review that questions the chosen implementation and design.