agentleFS
Sign inStart free
SECRET4422SECRET4422/loopbreaker/skills/loop-breaker/SKILL.md

loop-breaker

Skill1 starsChanged 2 months agoMITView on GitHub

Detect and break out of AI trial-and-error bug loops, code oscillation, and circular edits. Use when encountering repeating errors, when code edits keep breaking previously working features, or to revert to pre-loop snapshots.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. aradmanamnaoon/vibe-coding-skills★ 0same name
    2. owen-dev-6174/bodhisattva-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When an agent notices it is modifying the same file $\ge 3$ times to fix the same error.

    line 17
  2. Distinctive:

    When an edit to fix Feature A accidentally breaks Feature B.

    line 18
  3. Distinctive:

    When you need to restore the last clean project snapshot before an AI regression bug.

    line 19
  4. Very specific:

    When loopbreaker triggers an oscillation alert:

    line 40
  5. Distinctive:

    Halt Immediate Patching: Do NOT apply another micro-patch to the same file.

    line 42
  6. Distinctive:

    Check if two components are fighting over state ownership.

    line 44
  7. Very specific:

    Check if a useEffect or hook dependency array has circular dependencies.

    line 45
  8. Very specific:

    Run npx loopbreaker rollback to reset the file to its clean pre-loop state.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LoopBreaker Agent Skill

This skill guides AI coding agents on how to use loopbreaker to detect cognitive oscillation loops, halt trial-and-error spirals, and restore working snapshots.

When to Use

  • When an agent notices it is modifying the same file $\ge 3$ times to fix the same error.
  • When an edit to fix Feature A accidentally breaks Feature B.
  • When you need to restore the last clean project snapshot before an AI regression bug.

Quick CLI Reference

# Start background watcher
npx loopbreaker

# Revert to last clean pre-loop snapshot
npx loopbreaker rollback

# View history of recent file snapshots
npx loopbreaker history

Self-Correction Loop for AI Agents

When loopbreaker triggers an oscillation alert:

  1. Halt Immediate Patching: Do NOT apply another micro-patch to the same file.
  2. Isolate the Architectural Conflict:
    • Check if two components are fighting over state ownership.
    • Check if a useEffect or hook dependency array has circular dependencies.
  3. Execute Clean Rollback: Run npx loopbreaker rollback to reset the file to its clean pre-loop state.
  4. Apply Root-Cause Refactor: Extract shared logic into a standalone provider/module rather than continuing inline patching.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free