by harness · Agent Tool · ★ 115
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/harness/harness-skills.gitTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 115 |
| Forks | 23 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 73/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-14 |
| Created | 2026-03-11 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~17k |
Harness Skills Claude Code skills for the Harness.io CI/CD platform. Generate pipeline YAML, manage resources, debug failures, analyze costs, and more from natural language. This repository is designed as a workflow system, not just a folder of prompts.
Looking for a harness-skills alternative? If you're comparing harness-skills with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🚀 Universal SDK for building next-gen MCP servers
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude
lunar.dev: Agent native MCP Gateway for governance and security
Docfork - Up-to-date docs for AI Coding Agents.
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - imple
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and th
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: