Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by dataelement · Codex Skill · ★ 4.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Clawith safe to install? View the security audit →
<a href="https://discord.gg/NRN
| Stars | 4,137 |
| Forks | 692 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 61.8523693791623/100 |
| Open Issues | 326 |
| Last Updated | 2026-08-27 |
| Created | 2026-03-03 |
| Platforms | python |
| Est. Tokens | ~16k |
Looking for a Clawith alternative? If you're comparing Clawith 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.
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
An Agentic Framework for Reflective PowerPoint Generation
AI coworker with memory and collaboration
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Build autonomous AI agents in Python.
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
Explore other popular codex skill tools:
Clawith is Your First AI Agents Company. It is categorized as a Codex Skill with 4.1k GitHub stars.
Clawith is primarily written in Python. It covers topics such as agent, llm, multiagent.
You can find installation instructions and usage details in the Clawith GitHub repository at github.com/dataelement/Clawith. The project has 4.1k stars and 692 forks, indicating an active community.
Clawith is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Clawith on Agent Skills Hub include AI-Infra-Guard, PPTAgent, rowboat. 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: