# self-improvement-loops

> Claude/Codex skill by [@muratcankoylan](https://omgskills.com/library/muratcankoylan/index.md) · 18k stars · Updated 2026-10-12

This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.

## Install

```sh
git clone https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering /tmp/Agent-Skills-for-Context-Engineering && ln -s /tmp/Agent-Skills-for-Context-Engineering/skills/self-improvement-loops ~/.claude/skills/self-improvement-loops
```

## From README

Self-Improvement Loops This skill covers systems where the harness is the artifact being optimized: an agent mines its own failures and edits its own scaffold, a meta-agent searches over harness code, a population of workflow candidates evolves against an evaluator, or the mechanism that produces context is itself versioned and improved. The design question shifts from "how do I control one loop" (harness-engineering) to "how do I let a loop rewrite parts of itself without corrupting the signal that steers it". The controlling constraint across every published system: the loop optimizes whatever signal it is given, including the signal's own weaknesses. Design the loop assuming the optimizer will find every gap between the metric and the intent.

## Links

- HTML page: https://omgskills.com/library/muratcankoylan/agent-skills-for-context-engineering/skills/self-improvement-loops/
- GitHub: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
- Author: [@muratcankoylan](https://omgskills.com/library/muratcankoylan/index.md)

## More from this repo

- [context-engineering-collection](https://omgskills.com/library/muratcankoylan/agent-skills-for-context-engineering/index.md) — A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and...
   - [@muratcankoylan](https://omgskills.com/library/muratcankoylan/index.md) · 18k stars
- [long-horizon-prompting](https://omgskills.com/library/muratcankoylan/agent-skills-for-context-engineering/skills/long-horizon-prompting/index.md) — This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent...
   - [@muratcankoylan](https://omgskills.com/library/muratcankoylan/index.md) · 18k stars
- [context-compression](https://omgskills.com/library/muratcankoylan/agent-skills-for-context-engineering/skills/context-compression/index.md) — This skill should be used when long-running agent sessions need context compression, structured summarization,...
   - [@muratcankoylan](https://omgskills.com/library/muratcankoylan/index.md) · 18k stars