Назад към всички

Loop

// Run iterative agent loops until success criteria are met. Controlled autonomous iteration.

$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
nameLoop
slugloop
version1.0.2
descriptionRun iterative agent loops until success criteria are met. Controlled autonomous iteration.
changelogFixed internal contradiction about Git commits in memory.md
metadata[object Object]

Data Storage

~/loop/
├── active.json         # Currently running loops
├── history/            # Completed loop logs
│   └── {loop-id}.json
└── learnings.md        # Cross-loop patterns

Create on first use: mkdir -p ~/loop/history

Scope

This skill:

  • ✅ Runs iterative attempts toward defined success criteria
  • ✅ Logs each iteration with learnings
  • ✅ Exits on success, max iterations, or unrecoverable error
  • ❌ NEVER makes Git commits automatically
  • ❌ NEVER deploys to production
  • ❌ NEVER modifies system configuration
  • ❌ NEVER runs indefinitely (max 10 iterations hard limit)

Quick Reference

TopicFile
Loop examplesexamples.md
Memory between iterationsmemory.md

Core Rules

1. Pattern

Task + Criteria → Execute → Verify → [Pass? Exit : Retry]

2. Required Setup

ElementRequiredExample
TaskYes"Fix failing tests"
Success criteriaYes"All tests pass"
Max iterationsDefault: 5Max: 10
Verify commandRecommendednpm test

3. When to Propose

  • Task has clear success criteria but uncertain path
  • Previous attempt failed but error is fixable
  • User says "keep trying until..."

NOT for: One-shot tasks, undefined goals, exploratory work

4. Each Iteration

  1. Fresh context — Only carry: task, criteria, count, learnings
  2. Execute — Attempt the task
  3. Verify — Check success criteria
  4. Record — Append to history: what worked, what failed
  5. Decide — Pass? Exit. Fail? Retry if under limit.

5. Stopping Conditions

  • ✅ Success criteria met
  • ❌ Max iterations reached
  • ⚠️ Unrecoverable error (missing dependency, permission denied)

6. On Failure

If max reached without success:

  • Summarize all attempts
  • Identify common failure pattern
  • Recommend manual intervention or different approach

7. Safety

  • Hard limit: 10 iterations maximum
  • No destructive actions without explicit per-action approval
  • Log everything to ~/loop/history/