by openwalrus · Codex Skill · ★ 91
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: install step in a code block runs a script from an untrusted host. 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 | 91 |
| Forks | 13 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 62/100 |
| Open Issues | 2 |
| Last Updated | 2026-03-10 |
| Created | 2025-01-01 |
| Platforms | rust |
| Est. Tokens | ~148k |
Crabtalk [![Crates.io][crates-badge]][crates] [![Docs][docs-badge]][docs] [![Discord][discord-badge]][discord] Agent daemon. Runs agents, dispatches tools, connects to MCP servers. Start it, talk to it, extend it with packages. Or and use it to pull the rest. See the [installation guide][install] for details. Quick Start Full config reference: .
Looking for a walrus alternative? If you're comparing walrus 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 simple and well-tailored LLM application framework that enables you to seamlessly integrate LLM capabilities
AI agent tooling for data engineering workflows.
An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c
12306 MCP Server 是一个基于 Model Context Protocol (MCP) 的高性能火车票查询后端系统。它通过标准化接口提供官方 12306 的实时数据服务，包括余票查询、车站信息
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few
An MCP server for loading skills (shim for non-claude clients).
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: