Put build and test commands in your agent rules file before big changes
Rajesh7113's checklist before a coding agent touches a big change: tests pass on a clean branch, build and test commands are in CLAUDE.md or AGENTS.md, and one task per session.
Source
@Rajesh7113 on X · 2026-10-19
Written in our own words. Credit to the original author. Link checked 2026-10-24.
What they did
Rajesh7113's checklist before a coding agent touches a big change: tests pass on a clean branch, build and test commands are in CLAUDE.md or AGENTS.md, and one task per session.
Result (as claimed)
Fewer broken changes from coding agents.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
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 Claude Code, Codex. 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: Put build and test commands in your agent rules file before big changes What the original author did: Rajesh7113's checklist before a coding agent touches a big change: tests pass on a clean branch, build and test commands are in CLAUDE.md or AGENTS.md, and one task per session. Reported result (as claimed by the author): Fewer broken changes from coding agents. Source: https://x.com/Rajesh7113/status/2112100439055651009 Tools they used: Claude Code, Codex 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: Put build and test commands in your agent rules file before big changes What the original author did: Rajesh7113's checklist before a coding agent touches a big change: tests pass on a clean branch, build and test commands are in CLAUDE.md or AGENTS.md, and one task per session. Reported result (as claimed by the author): Fewer broken changes from coding agents. Source: https://x.com/Rajesh7113/status/2112100439055651009 Tools they used: Claude Code, Codex 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: Put build and test commands in your agent rules file before big changes What the original author did: Rajesh7113's checklist before a coding agent touches a big change: tests pass on a clean branch, build and test commands are in CLAUDE.md or AGENTS.md, and one task per session. Reported result (as claimed by the author): Fewer broken changes from coding agents. Source: https://x.com/Rajesh7113/status/2112100439055651009 Tools they used: Claude Code, Codex 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 write a CLAUDE.md or AGENTS.md rules file · How to run multiple coding agents together · How to save, share and resume coding agent sessions · How to use Claude Code and Codex together
Related use cases
Let your coding agent fetch skills on demand over MCP
Skillstore serves agent skills over MCP so tools like Claude Code and Codex can pull in a skill when a task needs it.
See which coding agent is waiting on you across all your computers
erzenkk built Overseer, a free MIT-licensed browser view of Claude Code, Codex and Gemini CLI sessions on all his computers, with approvals from his phone.
Install a skill so your coding agent can set up and write your docs
Mintlify released a skill that teaches Claude Code, Cursor and Codex to set up, write and customize Mintlify docs with the right config and components.
Have your agent search your past coding sessions on every prompt
Skillsync searches your past agent sessions on each prompt so lessons from earlier work come back automatically.