No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by cft0808 · Codex Skill · ★ 17.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is edict safe to install? View the security audit →
⚔️ 三省六部 · Edict 我用 1300 年前的帝国制度，重新设计了 AI 多 Agent 协作架构。结果发现，古人比现代 AI 框架更懂分权制衡。 12 个 AI Agent（11 个业务角色 + 1 个兼容角色）组成三省六部：太子分拣、中书省规划、门下省审核封驳、尚书省派发、六部+吏部并行执行。比 CrewAI 多一层制度性审核，比 AutoGen 多一个实时看板。 🎬 看 Demo · 🚀 30 秒体验 · 🏛️ 架构 · 📋 看板功能 · 📚 架构文档 · English · 参与贡献 <img src="https://img.shields.io/badge/公众号-cft0808-07C160?style=for-t
| Stars | 16,961 |
| Forks | 1,765 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 61.6720614373503/100 |
| Open Issues | 14 |
| Last Updated | 2026-09-28 |
| Created | 2026-02-23 |
| Platforms | claude-code, python |
| Est. Tokens | ~18k |
Looking for a edict alternative? If you're comparing edict 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.
CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and bu
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Multi-Agent Harness for Production AI
Build autonomous AI agents in Python.
Explore other popular codex skill tools:
edict is 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails. It is categorized as a Codex Skill with 17.0k GitHub stars.
edict is primarily written in Python. It covers topics such as ai-agents, ai-orchestration, autonomous-agents.
You can find installation instructions and usage details in the edict GitHub repository at github.com/cft0808/edict. The project has 17.0k stars and 1765 forks, indicating an active community.
edict is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to edict on Agent Skills Hub include chatgpt-on-wechat, gptme, ruflo. 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: