This plugin extends that arc into a competing coding environment: Codex can now be called for review or delegated work without requiring developers to abandon Claude Code as their primary interface.
First-order effects
Claude Code users can invoke Codex for code review and delegated tasks from within their existing workflow, reducing the friction of using both tools on the same project.
OpenAI gains a distribution path for Codex inside Claude Code, while Claude Code becomes a host surface for a third-party coding agent.
Second-order effects
Developers can split coding work across agents based on task or preference, making the surrounding workflow and context handoff more important than a single assistant's interface.
Coding-agent providers face greater pressure to support interoperable invocation and delegation, rather than assuming users will commit to one proprietary work surface.
Third-order effects
If cross-agent plugins become common, developer tooling may compete increasingly on orchestration, permissions, and shared project context—not only on the underlying model.
This is a step toward multi-agent development environments, though its durability depends on whether integrations preserve enough context and reliability for real engineering work.
The trend: AI coding tools are shifting from standalone assistants toward interoperable agent layers embedded in the developer environments teams already use.
I built a new plugin! You can now trigger Codex from Claude Code! Use the Codex plugin for Claude Code to delegate tasks to Codex or have Codex review your changes using your ChatGPT subscription. Start by installing the plugin: https://github.com/... [video]
Starting today you can use Codex in Claude Code 👀 /plugin marketplace add openai/codex-plugin-cc Try it out today with: /codex:review for a normal read-only Codex review /codex:adversarial-review for a steerable challenge review /codex:rescue to let codex rescue your code [video]
We've seen Claude Code users bring in Codex for code review and use GPT-5.4 for more complex tasks, so we thought: why not make that easier? Today we're open sourcing a plugin for it! You can call Codex from Claude Code with your ChatGPT subscription. We love an open ecosystem!
This is built on top of the Codex app server. It's the same server that powers Codex integrations in our own products like Codex app and external ones incl. Jetbrains and even T3 Code. It's fully open source and includes sign in with ChatGPT. So you can build this into
mh interesting. the codex plugin for claude code doesn't use the codex mcp server. codex team wrapped the codex app-server instead. building that app server infra open sourcing it was one of their smartest decisions.
This looks useful (Claudex?) Using both models almost daily - very different “personalities”, like asking two different developers to review/plan how to fix things
We love an open ecosystem! The Codex plugin is built on top of the Codex app server so it uses the same open-source agent harness as the rest of Codex. It means you can run multiple Codex tasks in parallel in the background, use the same models and the same Codex code review [ima…
You can now experience the power of codex while the little orange thing keeps you company. Works with your ChatGPT subscription, just as everywhere else. Clearly proof you can just build things. Have fun
My favorite thing about this plugin is that it's built on the open-source Codex app server and the same open-source Codex harness. So you get the same models, parallel tasking, and code review flow. Get the plugin here: https://github.com/...
I find the “Claude Code for codegen and Codex for review” narrative fascinating. Our models being good at reviewing code is downstream of them being good at *writing* code. You want your staff engineers reviewing all the code, so I get that. But you'd also want them writing all
OpenAI released a plugin that allows you to use Codex to review code generated by Claude Code. — I assume this is some snarky way of implying you need OpenAI's coding agent to review the bad code generated by Anthropic's. — Pettiness abounds.
wait so OpenAI is shipping plugins for Anthropic's tool now? the competitive dynamics here are genuinely bizarre. imagine Ford building a better cupholder for the Camry