OpenAI built a plugin that runs Codex inside Claude Code — teams are stacking tools, not picking one

OpenAI released an official, open-source plugin that runs Codex directly inside Anthropic's Claude Code, letting developers get a second AI opinion or hand off review without leaving their main tool. It's evidence that engineering teams are running multiple AI coding tools together rather than standardising on a single vendor.

OpenAI released an official plugin, codex-plugin-cc, that runs its Codex agent directly inside Anthropic’s competing Claude Code tool. It’s open source, requires only a ChatGPT subscription (including the free tier) or an OpenAI API key plus Node.js 18.18+, and adds slash commands including /codex:review for a standard code review, /codex:adversarial-review for a more skeptical second opinion, and /codex:rescue, which hands a task to Codex as a subagent entirely.

Why a company builds a plugin for a rival’s platform

The practical reason is adoption: with Claude Code established as the tool developers reach for first, a plugin that meets them there gets OpenAI’s technology in front of users who wouldn’t otherwise install it standalone. But the more useful reading is what it confirms about how engineering teams actually work now. Cursor rebuilt its interface for orchestrating parallel agents the same week. Early adopters are running Cursor, Claude Code, and Codex together rather than committing to one — using each for what it does best, on the same codebase, in the same session.

So what

For anyone commissioning a build, “which AI coding tool does your development partner use” is fast becoming the wrong question — the useful one is whether they’re running a deliberate, multi-tool workflow with review and cross-checking built in, or locked into a single vendor’s blind spots. A second model reviewing the first model’s code, adversarially, is a meaningfully different quality bar than one agent shipping unchecked. We run Claude Code and Codex together as standard practice for exactly this reason. More on our approach on the AI-assisted development page, or get in touch to talk through a project.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work