Fix loop breaker
Give it a bug your AI keeps failing to fix. Get a three-try repair plan, proof it works and a way back.
Fix loop breaker is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by sickn33 · Level: advanced · Thinking: high
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
When your AI keeps patching the same bug and nothing changes, this gives it a strict way to stop guessing. You get a repair with proof that it worked and a tested way back. Before any edit, it records the bug, the exact command that shows it, and how to undo the change. Then it allows three attempts only. Each attempt needs a single cause, a prediction, the changed files, a quick check and a check on the real path, such as the deployed app. A fix counts only if the check can also fail on a known bad state. If the bug cannot be reproduced, it stops and says so.
You give it
- Description of the bug
- Command or steps that show the failure
- Repo or project access
- Rollback method (optional)
You get
- Repair contract with baseline result
- Log of up to three attempts with evidence
- Check that fails on bad state and passes on the fix
- Tested rollback
- Plain verdict: fixed, not fixed or inconclusive
Use it when
- Your AI agent keeps trying similar patches and the same error comes back.
- A small test passes but the live app still fails.
- You need proof that a fix works, not only a claim.
- You want a rollback that has been tested before you trust a change.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and read your project files.