codex

Codex plugin for Claude Code — Fable control-plane fork

Fork of openai/codex-plugin-cc that adds a token-efficient control-plane for orchestrator models (Fable/Opus) that manage Codex as a worker fleet: live turn steering, bounded thread viewers, drift alerts, and explicit thread continuation. All upstream commands are unchanged.

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:review for a normal read-only Codex review
• /codex:adversarial-review for a steerable challenge review
• /codex:rescue, /codex:transfer, /codex:status, /codex:result, and /codex:cancel to delegate work, hand off sessions, and manage background jobs

Fork additions (control-plane):

• /codex:steer <job-id> -- <short correction> steers the active turn of a running background job via app-server turn/steer (works through the shared broker while the job's stream is active)
• /codex:threads, /codex:thread <id>, /codex:turns <id>, /codex:items <id> read Codex threads as compact, paginated, budget-bounded slices — never a full transcript dump
• /codex:tail [job-id] shows the last N job log lines locally
• /codex:alerts [job-id] reports drift as compact alerts: stalls, repeated failing commands, Codex errors, long runtimes — each with evidence and a suggested action
• /codex:continue <thread-id> [prompt] starts a follow-up turn on a specific existing thread (the honest fallback when a job already finished and cannot be steered)
• /codex:goal set|show|clear manages a persistent thread goal (native Codex thread/goal support) that anchors long-running loops; goal drift (blocked, budget-limited) surfaces in /codex:alerts
• /codex:artifacts [job-id] lists the evidence files (screenshots, reports) a job saved under .codex-artifacts/<job-id>/
• Sandbox trust model: /codex:setup --sandbox full makes every job run with full permissions (danger-full-access, no prompts); per-call --full/--write/--sandbox <mode> override. --worktree isolates a job in its own git worktree instead of a sandbox

Requirements

• ChatGPT subscription (incl. Free) or OpenAI API key.
  • Usage will contribute to your Codex usage limits. Learn more.
• Node.js 22.18 or later. The plugin runtime is native .mts TypeScript executed by Node's type stripping, with no build step or compiled output.

Install

Add the marketplace in Claude Code:

/plugin marketplace add andrewmaspero/codex-plugin-cc

Install the plugin:

/plugin install codex@codex-fable

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.

It can be used to pressure-test assumptions, tradeoffs, failure modes, and whether a different approach would have been safer or simpler.

It uses the same review target selection as /codex:review, including --base <ref> for branch review. It also supports --wait and --background. Unlike /codex:review, it can take extra focus text after the flags.

Use it when you want: