Edict (三省六部) Multi Agent Orchestration Skill by [ara.so](https://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](https://openclaw.ai), it provides a real time React kanban dashboard, full audit trails, and per agent LLM configuration. Architecture Overview Key differentiator vs CrewAI/AutoGen : Menxia (门下省) is a mandatory quality gate — it can veto and force rework before tasks reach executors. Prerequisites [OpenClaw](https://openclaw.ai) installed and running Python 3.9+ Node.js 18+ (for React dashboard build) macOS or Linux Installation Quick Demo (Docker — no OpenClaw needed) Open http://localhost:7891 Full Installation The install script automatically: Creates all 12 agent workspaces (taizi, zhongshu, menxia, shangshu, hubu, libu, bingbu, xingbu, gongbu, libu2, zaochao, legacy compat) Writes SOUL.md role definitions to each agent workspace Registers agents and permission matrix in openclaw.json Symlinks shared data directories across all agent workspaces Sets sessions.visibility all for inter agent message routing Syncs API keys across all agents Builds React frontend Initializes data directory and syncs official stats First time API Key Setup Running the System Key Commands OpenClaw Agent Management Dashboard Server Data Scripts Configuration Agent Model Configuration ( openclaw.json ) Per Agent Model Hot Switching (via Dashboard) Navigate to ⚙️ Models panel → select agent → choose LLM → Apply. Gateway restarts automatically (~5 seconds). Environment Variables Agent Roles Reference Agent Role Responsibility taizi 太子 Crown Prince Triage: chat → auto reply, edicts → create task zhongshu 中书省 Planning: decompose edict into subtasks menxia 门下省 Review/Veto : quality gate, can reject and force rework shangshu 尚书省 Dispatch: assign subtasks to ministries hubu 户部 Ministry of Revenue Finance, data analysis tasks libu 礼部 Ministry of Rites Communication, documentation tasks bingbu 兵部 Ministry of War Strategy, security tasks xingbu 刑部 Ministry of Justice Review, compliance tasks gongbu 工部 Ministry of Works Engineering, technical tasks libu2 吏部 Ministry of Personnel HR, agent management tasks zaochao 早朝官 Morning briefing aggregator Permission Matrix (who can message whom) Task State Machine Real Code Examples Send an Edict Programmatically Read Kanban State Update Task Status (with validation) Dashboard REST API Client Agent Health Check Custom SOUL.md (Agent Personality) Dashboard Panels Panel URL Fragment Key Features Kanban kanban Task columns, heartbeat badges, filter/search, pause/cancel/resume Monitor monitor Agent health cards, task distribution charts Memorials memorials Completed task archive, 5 stage timeline, Markdown export Templates templates 9 preset edict templates with parameter forms Officials officials Token usage ranking, activity stats News news Daily tech/finance briefing, Feishu push Models models Per agent LLM switcher (hot reload ~5s) Skills skills View/add agent skills Sessions sessions Live OC session monitor Court court Multi agent discussion around a topic Common Patterns Pattern 1: Parallel Ministry Execution Pattern 2: Menxia Veto Loop Pattern 3: News Aggregation + Push Troubleshooting exec format error in Docker Agents not receiving messages API key not propagated to all agents Dashboard shows stale data React frontend not built Invalid state transition error Gateway restart after model change Project Structure

edict-multi-agent-orchestration