Clean up a sloppy AI-built codebase by pointing Codex at Clean Code
Instead of listing rules, a developer told Codex to follow the principles of Robert Martin's Clean Code and refactor a large codebase he had built with AI since 2023 that had turned into a pile of slop.
Source
@Al_Grigor on X · 2026-10-22
Written in our own words. Credit to the original author. Link checked 2026-10-22.
What they did
Instead of listing rules, a developer told Codex to follow the principles of Robert Martin's Clean Code and refactor a large codebase he had built with AI since 2023 that had turned into a pile of slop.
Result (as claimed)
Took two banked Codex resets; the code became readable again.
Tools they used
Cost: OpenAI Codex: free plan, paid from $8/mo. Checked 2026-10-14.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up OpenAI Codex, ChatGPT. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
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: Clean up a sloppy AI-built codebase by pointing Codex at Clean Code What the original author did: Instead of listing rules, a developer told Codex to follow the principles of Robert Martin's Clean Code and refactor a large codebase he had built with AI since 2023 that had turned into a pile of slop. Reported result (as claimed by the author): Took two banked Codex resets; the code became readable again. Source: https://x.com/Al_Grigor/status/2113269186432778394 Tools they used: OpenAI Codex, ChatGPT Category: Dev & ops 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: Clean up a sloppy AI-built codebase by pointing Codex at Clean Code What the original author did: Instead of listing rules, a developer told Codex to follow the principles of Robert Martin's Clean Code and refactor a large codebase he had built with AI since 2023 that had turned into a pile of slop. Reported result (as claimed by the author): Took two banked Codex resets; the code became readable again. Source: https://x.com/Al_Grigor/status/2113269186432778394 Tools they used: OpenAI Codex, ChatGPT Category: Dev & ops 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: Clean up a sloppy AI-built codebase by pointing Codex at Clean Code What the original author did: Instead of listing rules, a developer told Codex to follow the principles of Robert Martin's Clean Code and refactor a large codebase he had built with AI since 2023 that had turned into a pile of slop. Reported result (as claimed by the author): Took two banked Codex resets; the code became readable again. Source: https://x.com/Al_Grigor/status/2113269186432778394 Tools they used: OpenAI Codex, ChatGPT Category: Dev & ops 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 use ChatGPT for real projects and everyday tasks · How to run multiple coding agents together
Related use cases
Let an agent operate Android apps on the phone itself
Opposable is an Android app that reads the screen through the accessibility service and taps and types in other apps. Claude, ChatGPT or Codex can drive it from a computer, and with none connected a 2B screen model runs the same loop on the phone with no server.
Build free dictation for every Mac app after leaving the Codex app
After moving from the Codex app to T3 Code, a developer missed ChatGPT's dictation, so he built GPT Voice: press a shortcut, speak, and the transcription is pasted wherever you're typing in any Mac app.
Have a second AI review your agent-built app as if it must handle 10x the data
The footage search Claude Code built him looked done, until a second AI found every vector held in RAM, 8 to 10 GB at 1,000 hours of footage by Claude's estimate. His review prompt: list each problem as a numbered fix with the file, why and the exact change.
Get daily summaries of what you built with Claude Code and Codex
AI WorkLog is a free open-source macOS app for Claude Code and Codex users with daily AI work summaries, project tracking, conversation search and token and cost analytics.