Run an autonomous science loop in Claude Code for three days with Codex checking the evidence
A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub.
Source
@Sanemavcil on X · 2026-10-18
Written in our own words. Credit to the original author. Link checked 2026-10-18.
What they did
A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub.
Result (as claimed)
Three days of continuous work; the post credits @curiouswavefn.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo.
Set it up
Gather your sources
Collect the papers, notes, links or files you want to work from in one place.
Load them into the tool
Open Claude Code, OpenAI Codex and add your sources. Keep the original files so you can check claims later.
Ask focused questions
Ask for summaries, comparisons or connections with citations to the source passages.
Verify and save
Spot check claims against the sources, then save the output as notes you can reuse.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Run an autonomous science loop in Claude Code for three days with Codex checking the evidence What the original author did: A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub. Reported result (as claimed by the author): Three days of continuous work; the post credits @curiouswavefn. Source: https://x.com/Sanemavcil/status/2111833021988929731 Tools they used: Claude Code, OpenAI Codex Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Run an autonomous science loop in Claude Code for three days with Codex checking the evidence What the original author did: A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub. Reported result (as claimed by the author): Three days of continuous work; the post credits @curiouswavefn. Source: https://x.com/Sanemavcil/status/2111833021988929731 Tools they used: Claude Code, OpenAI Codex Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Run an autonomous science loop in Claude Code for three days with Codex checking the evidence What the original author did: A creator ran an autonomous science workflow in Claude Code for three days straight, with Codex driving it and checking the evidence each round. The loop is open source on GitHub. Reported result (as claimed by the author): Three days of continuous work; the post credits @curiouswavefn. Source: https://x.com/Sanemavcil/status/2111833021988929731 Tools they used: Claude Code, OpenAI Codex Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to vibe code an app with Claude Code ยท How to run multiple coding agents together
Related use cases
Benchmark how much extra code AI models add
Built Parsimony, an open benchmark that scores how much unnecessary code models insert beyond solving the task.
Put Claude Code, Codex and a local model in one group chat you control from your phone
RAPR AI puts Claude Code, Codex and Ollama in one group chat on your own machine, controlled from your browser, Telegram or WhatsApp.
Check on Claude Code and Codex sessions from your phone without SSH keys
For people running agents in tmux and checking on them with Termius and Tailscale, Tenax lets you sign in and see your sessions without SSH keys or a VPN. It pings you when an agent needs you or finishes.
Run Claude Code, Codex, OpenCode and Pi in one workflow that ends in a pull request
Aqorin 0.3.0 is a TUI and CLI that gives each role its own runtime and model, sandboxes writes on macOS, lets your own checks decide when work passes, and turns a finished run into a pull request.