Edict Multi Agent Orchestration

This implements the Tang Dynasty's three departments and six ministries governance model as a multi-agent pipeline on OpenClaw. You get 12 specialized agents with a mandatory review gate: Crown Prince triages incoming requests, Zhongshu plans, Menxia reviews and can veto work back for revision, Shangshu dispatches to six execution ministries, and everything flows through a real-time kanban dashboard with full audit trails. The veto gate is the interesting bit here compared to CrewAI or AutoGen, where tasks can't reach executors without passing quality review. Ships with Docker demo, permission matrix enforced by the gateway, and per-agent LLM hot-swapping. Overkill for simple workflows, but if you need structured handoffs with accountability, the enforced state machine prevents agents from skipping steps.

skills.sh installs: 1.4K
GitHub stars: 61
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill edict-multi-agent-orchestration --agent claude-code

Installs into .claude/skills of the current project.

Files

Edict (三省六部) Multi-Agent Orchestration

Skill by ara.so — Daily 2026 Skills collection.

Edict implements a 1400-year-old Tang Dynasty governance model as an AI multi-agent architecture. Twelve specialized agents form a checks-and-balances pipeline: Crown Prince (triage) → Zhongshu (planning) → Menxia (review/veto) → Shangshu (dispatch) → Six Ministries (parallel execution). Built on OpenClaw, it provides a real-time React kanban dashboard, full audit trails, and per-agent LLM configuration.

Architecture Overview

You (Emperor) → taizi (triage) → zhongshu (plan) → menxia (review/veto)
             → shangshu (dispatch) → [hubu|libu|bingbu|xingbu|gongbu|libu2] (execute)
             → memorial (result archived)

Key differentiator vs CrewAI/AutoGen: Menxia (门下省) is a mandatory quality gate — it can veto and force rework before tasks reach executors.