> ## Documentation Index
> Fetch the complete documentation index at: https://smithers.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Ghost: Claude Code Plugin, Smithers Skill

> Example from ~/.claude/plugins/smithers/. A Claude Code plugin that teaches Claude how to create and monitor Smithers orchestrations.

# Claude Code Plugin: Smithers Skill

<Note>
  **Ghost doc.** Real Claude Code plugin at `~/.claude/plugins/smithers/`, registering the `smithers` skill to create and run workflows.
</Note>

## plugin.json

```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
{
  "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"]
}
```

## SKILL.md

```markdown theme={"theme":{"light":"github-light","dark":"github-dark"}}
---
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`
```

## EXAMPLES.md

Five complete workflow examples (see `~/.claude/plugins/smithers/skills/smithers/EXAMPLES.md` for full code):

1. **Simple Sequential**: Three-phase research/implement/test pipeline
2. **Conditional Branching**: Branches based on analysis results
3. **Parallel Execution**: Frontend/backend/database agents simultaneously
4. **Error Handling and Retry**: Automatic retry with recovery fallback
5. **Data Flow Between Phases**: Requirements/design/implement/test with structured data passing

## REFERENCE.md

| Component / Utility | Purpose                                                                                          |
| ------------------- | ------------------------------------------------------------------------------------------------ |
| `<Ralph>`           | Loop controller: remounts children each iteration until no agents render or `maxIterations` hits |
| `<Claude>`          | Self-executing agent: runs on mount, calls `onFinished`/`onError`                                |
| `<Phase>`           | Semantic grouping for orchestration phases, used in monitor output                               |
| `<Step>`            | Fine-grained grouping within a phase                                                             |
| Zustand Store       | State management: drives phase transitions via `onFinished` callbacks                            |
| `RalphContext`      | Exposes iteration count and completion signalling                                                |
| `serialize()`       | Serializes the orchestration tree to an XML plan string                                          |