Skip to main content

​
Claude Code Plugin — Smithers Orchestrator

Ghost doc — This is a real Claude Code plugin found at ~/.claude/plugins/smithers-orchestrator/ on the development machine.

​
plugin.json

{
  "name": "smithers-orchestrator",
  "version": "1.0.0",
  "description": "Multi-agent orchestration framework using Smithers.",
  "author": "Smithers Framework Contributors",
  "license": "MIT",
  "skills": ["skills/smithers-orchestrator"]
}

​
Monitor Output Format

The orchestrator includes a monitoring system with structured output: 
[10:30:00] ◆ PHASE: Research      Status: STARTING
[10:30:01] ● AGENT: Claude        Status: RUNNING
[10:30:05] ⚡ TOOL CALL: Read     File: src/index.ts
[10:30:12] ✓ PHASE: Research      Status: COMPLETE

​
Workflow Template

The skill teaches this template for new orchestrations: 
import { createSmithers, Sequence, Task, Workflow } from "smithers-orchestrator";
import { ToolLoopAgent as Agent } from "ai";
import { anthropic } from "@ai-sdk/anthropic";
import { z } from "zod";

const { smithers, outputs } = createSmithers({
  research: z.object({ findings: z.string() }),
  summary: z.object({ text: z.string() }),
});

const researcher = new Agent({
  model: anthropic("claude-sonnet-4-5-20250929"),
  instructions: "Research the topic thoroughly.",
});

const writer = new Agent({
  model: anthropic("claude-sonnet-4-5-20250929"),
  instructions: "Write a clear, concise summary.",
});

export default smithers((ctx) => (
  <Workflow name="research-workflow">
    <Sequence>
      <Task id="research" output={outputs.research} agent={researcher}>
        {`Research: ${ctx.input.topic}`}
      </Task>
      <Task id="summarize" output={outputs.summary} agent={writer}>
        {`Summarize: ${ctx.outputMaybe("research", { nodeId: "research" })?.findings}`}
      </Task>
    </Sequence>
  </Workflow>
));

​
Best Practices

  1. Use createSmithers for schema-driven workflows with auto-persistence
  2. Use outputs.xxx as the output prop on <Task> (the Zod schema, not a string key)
  3. Use ctx.outputMaybe() for cross-task data flow (returns undefined if not yet available)
  4. Set maxIterations on <Loop> to prevent infinite loops
  5. Include continueOnFail on non-critical tasks

​
What This Demonstrates

  • Plan-as-code — The JSX program serves as both the execution plan and the runnable workflow.
  • Monitoring integration — Structured output format designed for both human and LLM consumption.
  • Correct API patterns — Uses createSmithers with Zod schemas, outputs.xxx references, and ctx.outputMaybe() for cross-task data flow.