Loop Agent

Loop Agent Skill

Execute workflow agents iteratively for refinement and progressive improvement until quality criteria are met.

Quick Reference

• [Modes](modes.md) - Loop termination modes (fixed, criteria, convergence, hybrid)
• [Patterns](patterns.md) - Common loop patterns (refinement, test-fix, optimization)
• [Configuration](configuration.md) - Loop setup and templates
• [Examples](examples.md) - Complete loop examples

When to Use

• Code needs iterative refinement until quality standards met
• Tests need repeated fix-validate cycles
• Performance requires progressive optimization
• Quality improvements need multiple passes
• Feedback loops necessary for convergence

NOT Appropriate For

• Single-pass tasks (use specialized agent)
• Purely parallel work (use agent-coordination)
• Simple linear workflows (use sequential)
• One-time analysis

Core Concepts

Loop Termination Modes

| Mode | Description | Use When | |------|-------------|----------| | Fixed | Run exactly N iterations | Known number of passes needed | | Criteria | Until success criteria met | Specific quality/performance targets | | Convergence | Stop at diminishing returns | Optimal result unknown | | Hybrid | Combine multiple conditions | Complex requirements |

See [modes.md](modes.md) for detailed mode documentation and [patterns.md](patterns.md) for common loop patterns.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: d-o-hub
• Source: d-o-hub/rust-self-learning-memory
• License: MIT
• Homepage: https://d-o-hub.github.io/rust-self-learning-memory/

Install and usage instructions live in the source repository linked above.