No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by tigerless-labs · Claude Skill · ★ 1.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is autoharness safe to install? View the security audit →
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 | 1,532 |
| Forks | 92 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 69.4947285752662/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-04 |
| Created | 2026-06-09 |
| Platforms | claude-code, python |
| Est. Tokens | ~14k |
Looking for a autoharness alternative? If you're comparing autoharness with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 gu
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified e
Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you thi
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 1.5k 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 1.5k stars and 92 forks, indicating an active community.
autoharness is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to autoharness on Agent Skills Hub include skills, code-graph-rag, mcp-context-forge. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: