by dedene · Codex Skill · ★ 139
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
brew install dedene/tap/claw-wrap
git clone https://github.com/dedene/claw-wrap.gitTaken from the project's README on GitHub.
Flagged: sudo usage. 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 | 139 |
| Forks | 6 |
| Language | Go |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 75/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-07 |
| Created | 2026-02-01 |
| Platforms | cli, go |
| Est. Tokens | ~18k |
claw-wrap A secure credential proxy for CLI tools and HTTP APIs. Executes tools with secrets on behalf of sandboxed processes, or injects credentials into HTTP requests via MITM proxy — credentials never enter the sandbox. Install · Config · Sandbox · Protocol The Problem You're running an AI agent in a sandbox. The agent needs to call to interact with GitHub — list repos, read issues, check PRs.
These tools work well together with claw-wrap for enhanced workflows:
Looking for a claw-wrap alternative? If you're comparing claw-wrap 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.
Think before doing, prove before saving. Vestige is the local-first cognitive operating system and determinist
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premi
🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autono
Official SonarQube MCP Server for code quality and security in AI agents
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunt
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: