Guide · AI
How to get Claude Code and Codex working together
By Ben Lane
Art: OpenAI, from the GPT-6 Astra launch page, and Anthropic, from the Claude Opus 5.5 launch page
Anthropic and OpenAI each make an AI model they call their most capable, and you can put both of them on the same job. Anthropic's is Claude Fable 5.1 and OpenAI's is GPT-6 Astra. Each one runs in its maker's coding tool: Claude Code for Anthropic, Codex for OpenAI. OpenAI makes a free add-on, called a plugin, that puts Codex inside Claude Code, so the two can share the work. Claude writes the plan and the two go through it until they agree. Then Codex builds it and Claude tests it. We tried it once on a small calculator page, and they fixed two mistakes in the plan before any code was written. This guide takes you from setup to the first piece of work the two of them make together.
All product names and marks belong to their owners. No affiliation is implied.
More guides
2 tools
How to choose Sonnet 5.5 or GPT-6.1 Sol for business automation
Give one real job from your business to both models, check what changed in your apps, and know which model should do it and what each run costs.
1 tool
How to run your firm's repetitive work with Claude Haiku 5.5
Hand one repetitive job in your firm to Claude Haiku 5.5: test it against answers your team already gave, work out what each item costs, then run the whole pile at once, paid from the monthly credit Max and Team plans now include.
4 tools
How to use Meta's Muse Spark Open, the best American open model
See how Meta's Muse Spark Open compares with ChatGPT, Claude and Gemini, test it on your own work, and keep your sensitive work where you control it.