by Orkas-AI · Codex Skill · ★ 9.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/Orkas-AI/Orkas.git
Taken from the project's README on GitHub. Check the security audit before running it.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 9,457 |
| Forks | 561 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63/100 |
| Open Issues | 19 |
| Last Updated | 2026-11-18 |
| Created | 2026-04-29 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~14k |
Orkas Open-source, local-first desktop app to build and command a team of AI agents — in one chat, with your own LLM keys. Fully offline-capable. macOS · Windows · Linux. English · 简体中文 A commander LLM assembles a team of sub-agents and dispatches them in parallel or in series. Agents self-evolve through reflection. Your conversations, files, and API keys never leave your machine.
Looking for a Orkas alternative? If you're comparing Orkas 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.
Where people and agents build in tune.
A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily n
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source P
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: