by poco-ai · Codex Skill · ★ 1.4k
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 | 1,356 |
| Forks | 129 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 65/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-19 |
| Created | 2026-01-08 |
| Platforms | browser, claude-code, python |
| Est. Tokens | ~14k |
Poco: Your Pocket Coworker A safer, more beautiful, and easier-to-use OpenClaw alternative English | 简体中文 Core Features Secure Sandbox All tasks run in an isolated container. Feel free to install dependencies, modify files, and execute commands — without affecting the host environment. More Than a Chatbot Supports Plan Mode, conversation queueing, conversation termination ...
Looking for a poco-claw alternative? If you're comparing poco-claw with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of toke
An open-source AI assistant framework with skills and agent architecture
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate
Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automa
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
Explore other popular codex skill 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: