by tigerless-labs · Claude Skill · ★ 11.1k
autoharness autoharness is a self-learning skill layer for Claude Code. It learns skills from your real sessions, merges same-scenario ones instead of stacking near-duplicates, updates them in use, and prunes any that stop getting used — so the layer stays clean on its own, touching only the skills it wrote itself. Same model, different harness — 42% → 78% on CORE-Bench (HAL). The harness does much of the work (swyx's Big Model vs Big Harness), yet it's still rebuilt by hand every model generation. autoharness bets one slice of it — the skill layer — can maintain itself. | Validated in use,
| Stars | 11,129 |
| Forks | 626 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 69.4947285752662/100 |
| Open Issues | 62 |
| Last Updated | 2026-10-15 |
| Created | 2026-06-09 |
| Platforms | claude-code, python |
| Est. Tokens | ~14k |
Explore other popular claude skill tools:
autoharness is Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.. It is categorized as a Claude Skill with 11.1k GitHub stars.
autoharness is primarily written in Python. It covers topics such as agent-skills, claude-code, claude-code-plugin.
You can find installation instructions and usage details in the autoharness GitHub repository at github.com/tigerless-labs/autoharness. The project has 11.1k stars and 626 forks, indicating an active community.
autoharness is released under the MIT license, making it free to use and modify according to the license terms.