by harnessclaw · Agent Tool · ★ 271
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 271 |
| Forks | 94 |
| Language | Go |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 72/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-30 |
| Created | 2026-04-12 |
| Platforms | browser, go |
| Est. Tokens | ~17k |
HarnessClaw Engine English | 中文 An LLM programming assistant engine built with Go. It provides capabilities via the WebSocket protocol, supporting multi-turn dialogues, tool calling, permission control, and skill extension. Architecture Overview Dependency Direction: Channel → Router → Engine → Provider / Tool (Unidirectional, no circular dependencies) Core Features 5-Phase Query Loop — Prep
Looking for a harnessclaw-engine alternative? If you're comparing harnessclaw-engine 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.
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI
Shell and coding agent on mcp clients
AI agent tutorials for backend developers without AI background. 适合后端工程师的零基础 AI Agent 教程
Aser is a lightweight, self-assembling AI Agent frame.
从零到工作流，掌握 AstronClaw（云端）与 Loomy（桌面）的 AI 助手实战教程 | A complete tutorial to master AstronClaw (cloud AI) & Loomy (
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: