skills.rest
drewid74
drewid74COMMUNITY
Explore all skills by this author →
GitHub

Orchestration Scaffold

Scaffold a Docker Compose AI orchestration stack integrating OpenCode with LangGraph and MCP servers.

8|1|Updated Mar 30, 2026
Search Tags:#multi-agent#orchestration#langgraph#docker compose#opencode#mcp servers#local llm
One-click install
npx skills add https://github.com/drewid74/ai_skills --skill orchestration-scaffold
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Orchestration Scaffold
Source: https://github.com/drewid74/ai_skills/tree/main/orchestration-scaffold
Command: npx skills add https://github.com/drewid74/ai_skills --skill orchestration-scaffold

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you scaffold a production-minded local AI orchestration stack by wiring together an orchestrator, a supervisor runtime, local inference, and MCP tool access with explicit safety and termination controls.

Core Features & Use Cases

  • Local multi-agent orchestration blueprint: Sets up an OpenCode developer interface that connects to a LangGraph supervisor via an A2A protocol, with a clean division between planning and execution models.
  • Tool access via MCP servers: Defines MCP filesystem and custom tool servers for workspace I/O and domain tooling, suitable for agent tool-calling workflows.
  • Production safety harness: Provides guardrails such as pre-tool-use hooks with blocklists, enforced loop termination budgets, generator/evaluator separation to prevent self-grading, and an explicit state handoff contract.
  • Operational readiness: Includes SLIs/alerts/runbook patterns plus observability components (Prometheus/Grafana/Loki) to validate task completion, latency, and error rates.

Quick Start

Use this Skill to have an AI generate a Docker Compose-based orchestration stack for your homelab and produce the required OpenCode and LangGraph integration files for multi-agent execution.

Frequently Asked Questions about Orchestration Scaffold

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up a local multi-agent orchestration stack with LangGraph and Docker Compose?▼

To set up local multi-agent orchestration, you can scaffold a Docker Compose stack integrating OpenCode with a LangGraph supervisor, MCP tool servers, and Ollama for local inference routing. This provides a complete homelab deployment with multi-agent task execution.

What is the best way to prevent infinite loops in local LLM multi-agent workflows?▼

To prevent infinite loops in multi-agent workflows, implement enforced loop termination budgets, pre-tool-use hooks with blocklists, and strict state handoff contracts. These safety controls ensure reliable task execution and prevent runaway agent processes.

Does this multi-agent orchestration scaffold support local inference routing with Ollama?▼

Yes, the orchestration scaffold supports local inference routing through Ollama with model split strategies. This allows you to route planning and execution tasks to different local models for optimized multi-agent performance.

How do I implement safety controls and monitoring for AI agent orchestration?▼

You can implement safety controls using pre-tool-use hooks, generator-evaluator separation to prevent self-grading, and SRE-style SLIs with alerts. The stack includes Prometheus, Grafana, and Loki for monitoring task completion, latency, and error rates.

Can I use MCP servers for tool access in a Docker Compose AI agent deployment?▼

Yes, you can define MCP filesystem and custom tool servers for workspace I/O and domain tooling within your Docker Compose deployment. This enables agent tool-calling workflows for multi-agent task execution in your homelab.

Related Skills

Explore More Software Engineering Skills→
mattwoodcomattwoodco
3

docker

Set up a Docker Compose local development environment with multiple services.

Community
Advanced
hashimichehashimiche
29

obs

Deploy a standalone Grafana, Prometheus, Loki, and Promtail observability stack for HAL.

Community
Advanced
OrcaQubitsOrcaQubits
35

a2a-framework-integration

Integrate Google ADK, LangGraph, CrewAI, AutoGen, and AWS Bedrock AgentCore agents into the A2A protocol.

Official
Advanced
timequitytimequity
6

devops

Automate containerized deployments using Docker and CI/CD pipelines.

Official
Advanced