Bootstrap all Heady services — start heady-manager, wire auto-success engine, verify health, and enable continuous pipeline operation
Bootstrap all Heady services — start heady-manager, wire auto-success engine, verify health, and enable continuous pipeline operation
npx skills add https://github.com/HeadyAI/Heady-Staging --skill heady-start复制此命令并粘贴到 Claude Code 中以安装该技能
Use when the user wants to turn repositories, technical notes, strategy files, or mixed project materials into structured knowledge packs, briefings, or LLM-ready documentation. Helpful for repo-to-docs workflows, NotebookLM or knowledge-base preparation, executive briefings, and documentation hubs that work for both technical and non-technical audiences.
Master orchestrator prompt for the Heady ecosystem. Universal coding agent system prompt for Claude, GPT, Gemini, Perplexity, Windsurf, Cursor, Copilot, and any agentic coding system. Synthesizes all 60+ Heady skills into a single cohesive autonomous builder prompt. Use for any Heady development, architecture, deployment, orchestration, vector memory, MCP gateway, edge AI, bee swarm, liquid node, CSL engine, phi-math, sacred geometry, or full-system build task. Keywords: heady, maximum potential, universal prompt, coding agent, autonomous builder, liquid OS, sacred geometry, CSL, phi-math, vector memory, bee swarm, MCP gateway, edge AI, conductor, pipeline, alive software.
Use when the user is working across multiple parts of the Heady ecosystem and needs coordinated planning, routing, synthesis, or delegation across research, architecture, patent, competitive, deployment, nonprofit, or product strategy work. Keywords include Heady, sovereign AI, agent swarm, orchestration, domain strategy, ecosystem planning, roadmap, integration plan, and multi-step execution.
Use when the user is working on the Heady ecosystem and wants deep technical or strategic research, current AI ecosystem analysis, patent-aware framing, or integration-aware answers tailored to Eric Head's sovereign AI platform. Triggers include Heady, HeadySystems, HeadyConnection, headyme, headymcp, Cloudflare, Cloud Run, pgvector, patent research, competitive analysis, vector memory, and multi-agent architecture.
Master orchestrator prompt for the Heady ecosystem. Universal coding agent system prompt for Claude, GPT, Gemini, Perplexity, Windsurf, Cursor, Copilot, and any agentic coding system. Synthesizes all 60+ Heady skills into a single cohesive autonomous builder prompt. Use for any Heady development, architecture, deployment, orchestration, vector memory, MCP gateway, edge AI, bee swarm, liquid node, CSL engine, phi-math, sacred geometry, or full-system build task. Keywords: heady, maximum potential, universal prompt, coding agent, autonomous builder, liquid OS, sacred geometry, CSL, phi-math, vector memory, bee swarm, MCP gateway, edge AI, conductor, pipeline, alive software.
Manage the always-on Auto-Success Engine — start, status, force-react, add tasks, and wire external systems
| name | heady-start |
| description | Bootstrap all Heady services — start heady-manager, wire auto-success engine, verify health, and enable continuous pipeline operation |
Bootstrap the full Heady ecosystem for continuous, autonomous operation. This skill starts the server, wires all systems, verifies health, and ensures HCFullPipeline + AutoSuccess Engine are running at max potential.
node --version (requires ≥18)package.json exists and dependencies installed: ls node_modules | head -5configs/hcfullpipeline.yamlconfigs/resource-policies.yamlconfigs/service-catalog.yamlconfigs/governance-policies.yamlconfigs/concepts-index.yamldata/ directory: ls data/ 2>/dev/null || mkdir -p data.env has required vars (check .env.example for the list)Run these checks BEFORE starting the server:
node --check src/hc_pipeline.js
node --check src/orchestration/hc_auto_success.js
node -e "require('./src/hc_pipeline.js')" 2>&1 | head -20
cd /home/user/Heady
# Option A: Direct (foreground, for debugging)
node heady-manager.js
# Option B: PM2 (background, auto-restart)
pm2 start heady-manager.js --name heady-manager
pm2 save
# Option C: Node with env
NODE_ENV=development node heady-manager.js
After start, verify:
curl -s http://localhost:3301/api/health | jq .
curl -s http://localhost:3301/api/auto-success/status | jq .status,.running
curl -s http://localhost:3301/api/pipeline/status | jq .
Trigger initial pipeline run:
curl -X POST http://localhost:3301/api/pipeline/run
curl -X POST http://localhost:3301/api/auto-success/force-react
Check that improvement lane is scheduled:
improvement lane: every 15 min (*/15 * * * *)system_operations lane: every 4 hours (0 */4 * * *)learning lane: 6AM daily (0 6 * * *)pqc lane: 2AM daily (0 2 * * *)| Service | Port | Path |
|---|---|---|
| heady-manager | 3301 | Main MCP+API server |
| heady-brain | 3311 | Brain/LLM routing |
| heady-memory | 3312 | Vector memory |
| auth-session | 3314 | Auth service |
| api-gateway | 3315 | API gateway |
| heady-buddy | 3326 | HeadyBuddy |
| heady-guard | 3329 | Security guard |
| hcfp | 3330 | HCFP service |
Symptom: SyntaxError: Cannot use import statement in a module loaded as CommonJS
Fix: Add "type": "module" to package.json OR convert imports to require()
Symptom: Error: Cannot find module 'js-yaml'
Fix: npm install
Symptom: Environment validation failed
Fix: cp .env.example .env then populate required vars
Symptom: Error: listen EADDRINUSE :::3301
Fix: kill $(lsof -ti:3301) then restart
Symptom: ENOENT: no such file or directory, open 'data/auto-success-tasks.json'
Fix: mkdir -p data
heady-manager.js — Main server entry pointsrc/hc_pipeline.js — Pipeline executorsrc/orchestration/hc_auto_success.js — Auto-success engine.env / .env.example — Environment configurationpackage.json — Dependencies and scriptsdocker-compose.yml — Full stack via Docker