Codex Delegate

Stop burning your frontier agent's limits on boilerplate.

Delegate implementation to the OpenAI Codex CLI — your agent writes the brief and reviews the diff.

Use your best coding agent where its judgment matters most: understanding the task, shaping the plan, and reviewing the result.

Codex Delegate is the MCP bridge that lets Claude Code, Cursor, Copilot — or any MCP client — hand implementation to the OpenAI Codex CLI, then get a clean, structured result back for review.

🧠 Frontier quality, kept

Your assistant does what frontier models are actually for: understands the task, writes a precise brief, reviews the finished diff. Codex holds its own as the implementer — guided and checked by a smarter orchestrator. The result reads like frontier work, because a frontier model planned it and signed off on it.

⚡ Done faster

Codex tears through multi-file edits while a frontier chat model would still be streaming the first file. You delegate, keep working with your assistant, and the diff shows up done.

🔋 Your limits stop being the bottleneck

Delegated work runs on the OpenAI Codex CLI and its own usage — separate from your orchestrator's chat quota. Your Claude, Cursor, or Copilot subscription spends tokens on the brief and the review; Codex does the grinding. On API? That's the per-token grind moved off your main bill.

Features

• 🤝 Native plugins — install into Claude Code, Cursor, or GitHub Copilot CLI and just say "delegate this to Codex". The shared skill teaches your agent how to delegate well.
• 📦 Clean, typed results — one compact JSON block: the final answer, status, the files Codex edited, and per-turn token counts. Fields that carry no signal are omitted, so anything present is worth reading.
• 📋 Four modes — agent edits, plan requests a schema-validated plan for you to review and approve, ask answers questions, and review runs Codex's own reviewer over uncommitted work, a base branch, or a single commit.
• 🧵 Resume — continue the same Codex thread with resumeThreadId, and get told if the context didn't actually carry over.
• 🧑‍🤝‍🧑 Parallel, and cancellable for real — fan a question across models or put independent workers on independent directories; cancel waits for the exit and warns when a process outlives the kill deadline.
• 🩺 Self-diagnosing — a doctor tool that tells you exactly what's missing if setup isn't right.
• 🔌 Works everywhere MCP does — VS Code, JetBrains, Windsurf, Visual Studio, and more.

The caveats are documented rather than buried: what an empty warnings does not prove, and when result is salvage instead of an answer, are in the delegate reference.

Install

You need Node.js 20+ and the OpenAI Codex CLI, already logged in (codex login).

Claude Code

/plugin marketplace add andreilungeanu/codex-delegate-mcp
/plugin install codex-delegate@codex-delegate-mcp

Then just ask:

Delegate to Codex: migrate src/api from callbacks to async/await and update the tests, then walk me through what changed.

That's the whole loop — Claude writes the brief, Codex grinds through the files, Claude walks you through the diff.

Cursor

Add an MCP server in Cursor Settings → MCP (or project .cursor/mcp.json):

{
  "mcpServers": {
    "codex-delegate": {
      "command": "npx",
      "args": ["-y", "codex-delegate-mcp"]
    }
  }
}

Then ask Cursor to delegate implementation to Codex the same way.

GitHub Copilot CLI

copilot plugin install andreilungeanu/codex-delegate-mcp

More clients

{
  "servers": {
    "codex-delegate": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "codex-delegate-mcp"]
    }
  }
}

{
  "mcpServers": {
    "codex-delegate": {
      "command": "npx",
      "args": ["-y", "codex-delegate-mcp"]
    }
  }
}

{
  "servers": {
    "codex-delegate": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "codex-delegate-mcp"]
    }
  }
}

Kiro, Kilo Code, and any other MCP client

Add the following server to the client's MCP config:

{
  "mcpServers": {
    "codex-delegate": {
      "command": "npx",
      "args": ["-y", "codex-delegate-mcp"]
    }
  }
}

MIT © Andrei Lungeanu

_{Configuration · Security · Privacy · Terms · Changelog}