by AISmithLab · Agent Tool · ★ 97
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.
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 | 97 |
| Forks | 4 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 62/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-21 |
| Created | 2025-10-25 |
| Platforms | python |
| Est. Tokens | ~567k |
Toward Precise and Consistent Agent Behaviors across Models Anchored by Validated Social Science Knowledge 🌐 Project Page: cobra.clawder.ai | 📄 Paper: arXiv 2509.13588 If you find CoBRA useful, please star ⭐ this repo to help others discover it! 💡 What is Cognitive Bias? Systematic deviations from rat
Looking for a CoBRA alternative? If you're comparing CoBRA 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.
MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured JSON configura
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spre
Transform your Claude Code terminal with atomic precision statusline. Features flexible layouts, real-time cos
18 Google Maps tools and 3 Agent Skills for place search, routes, travel planning, and local SEO—via MCP or st
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - imple
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: