{
  "name": "smithers",
  "version": "0.2.0",
  "description": "Durable control plane for long-running coding agents",
  "author": "Smithers",
  "license": "MIT",
  "repository": "https://github.com/smithersai/smithers",
  "keywords": ["orchestration", "multi-agent", "smithers", "workflow", "ai-agents", "claude", "jsx", "reactive"],
  "skills": ["skills/smithers"]
}

---
name: smithers
description: Create and monitor multi-agent AI orchestrations using Smithers framework. Use when user wants to coordinate multiple AI agents, create complex workflows, build agent pipelines, or mentions "smithers", "multi-agent", "orchestration", "workflow", "agent coordination". Strongly recommends plan mode for orchestrations with 3+ phases.
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
  - Task
user-invocable: true
recommend-plan-mode: true
---

# Smithers Orchestrator

## When to Use
- Orchestrate multiple AI agents working together
- Create complex multi-phase workflows
- Build agent pipelines with state management

## Quick Start
1. Initialize: `bunx smithers-orchestrator init` (installs the `.smithers/` pack: workflows, prompts, and UIs)
2. Edit `.smithers/workflows/*.tsx` (and their `.smithers/prompts/*.mdx`) to define your workflow
3. Run and monitor: `bunx smithers-orchestrator up <workflow>` then `bunx smithers-orchestrator monitor`