orchestrating-swarms

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

---

Primitives

Primitive	What It Is	File Location
Agent	A Claude instance that can use tools. You are an agent. Subagents are agents you spawn.	N/A (process)
Team	A named group of agents working together. One leader, multiple teammates.	~/.claude/teams/{name}/config.json
Teammate	An agent that joined a team. Has a name, color, inbox. Spawned via Task with team_name + name.	Listed in team config
Leader	The agent that created the team. Receives teammate messages, approves plans/shutdowns.	First member in config
Task	A work item with subject, description, status, owner, and dependencies.	~/.claude/tasks/{team}/N.json
Inbox	JSON file where an agent receives messages from teammates.	~/.claude/teams/{name}/inboxes/{agent}.json
Message	A JSON object sent between agents. Can be text or structured (shutdown_request, idle_notification, etc).	Stored in inbox files
Backend	How teammates run. Auto-detected: in-process (same Node.js, invisible), tmux (separate panes, visible), iterm2 (split panes in iTerm2). See Spawn Backends.	Auto-detected based on environment

How They Connect

flowchart TB
    subgraph TEAM[TEAM]
        Leader[Leader - you]
        T1[Teammate 1]
        T2[Teammate 2]

        Leader <-->|messages via inbox| T1
        Leader <-->|messages via inbox| T2
        T1 <-.->|can message| T2
    end

    subgraph TASKS[TASK LIST]
        Task1["#1 completed: Research<br/>owner: teammate1"]
        Task2["#2 in_progress: Implement<br/>owner: teammate2"]
        Task3["#3 pending: Test<br/>blocked by #2"]
    end

    T1 --> Task1
    T2 --> Task2
    Task2 -.->|unblocks| Task3

Lifecycle

flowchart LR
    A[1. Create Team] --> B[2. Create Tasks]
    B --> C[3. Spawn Teammates]
    C --> D[4. Work]
    D --> E[5. Coordinate]
    E --> F[6. Shutdown]
    F --> G[7. Cleanup]

Message Flow

sequenceDiagram
    participant L as Leader
    participant T1 as Teammate 1
    participant T2 as Teammate 2
    participant Tasks as Task List

    L->>Tasks: TaskCreate (3 tasks)
    L->>T1: spawn with prompt
    L->>T2: spawn with prompt

    T1->>Tasks: claim task #1
    T2->>Tasks: claim task #2

    T1->>Tasks: complete #1
    T1->>L: send findings (inbox)

    Note over Tasks: #3 auto-unblocks

    T2->>Tasks: complete #2
    T2->>L: send findings (inbox)

    L->>T1: requestShutdown
    T1->>L: approveShutdown
    L->>T2: requestShutdown
    T2->>L: approveShutdown

    L->>L: cleanup

---

Table of Contents

1. Core Architecture
2. Two Ways to Spawn Agents
3. Built-in Agent Types
4. Plugin Agent Types
5. TeammateTool Operations
6. Task System Integration
7. Message Formats
8. Orchestration Patterns
9. Environment Variables
10. Spawn Backends
11. Error Handling
12. Complete Workflows

---

Core Architecture

How Swarms Work

A swarm consists of:

• Leader (you) - Creates team, spawns workers, coordinates work
• Teammates (spawned agents) - Execute tasks, report back
• Task List - Shared work queue with dependencies
• Inboxes - JSON files for inter-agent messaging

File Structure

~/.claude/teams/{team-name}/
├── config.json              # Team metadata and member list
└── inboxes/
    ├── team-lead.json       # Leader's inbox
    ├── worker-1.json        # Worker 1's inbox
    └── worker-2.json        # Worker 2's inbox

~/.claude/tasks/{team-name}/
├── 1.json                   # Task #1
├── 2.json                   # Task #2
└── 3.json                   # Task #3

Team Config Structure

{
  "name": "my-project",
  "description": "Working on feature X",
  "leadAgentId": "team-lead@my-project",
  "createdAt": 1706000000000,
  "members": [
    {
      "agentId": "team-lead@my-project",
      "name": "team-lead",
      "agentType": "team-lead",
      "color": "#4A90D9",
      "joinedAt": 1706000000000,
      "backendType": "in-process"
    },
    {
      "agentId": "worker-1@my-project",
      "name": "worker-1",
      "agentType": "Explore",
      "model": "haiku",
      "prompt": "Analyze the codebase structure...",
      "color": "#D94A4A",
      "planModeRequired": false,
      "joinedAt": 1706000001000,
      "tmuxPaneId": "in-process",
      "cwd": "/Users/me/project",
      "backendType": "in-process"
    }
  ]
}

---

Two Ways to Spawn Agents

Method 1: Task Tool (Subagents)

Use Task for short-lived, focused work that returns a result:

Task({
  subagent_type: "Explore",
  description: "Find auth files",
  prompt: "Find all authentication-related files in this codebase",
  model: "haiku"  // Optional: haiku, sonnet, opus
})

Characteristics:

• Runs synchronously (blocks until complete) or async with run_in_background: true
• Returns result directly to you
• No team membership required
• Best for: searches, analysis, focused research

Method 2: Task Tool + team_name + name (Teammates)

Use Task with team_name and name to spawn persistent teammates:

// First create a team
Teammate({ operation: "spawnTeam", team_name: "my-project" })

// Then spawn a teammate into that team
Task({
  team_name: "my-project",        // Required: which team to join
  name: "security-reviewer",      // Required: teammate's name
  subagent_type: "security-sentinel",
  prompt: "Review all authentication code for vulnerabilities. Send findings to team-lead via Teammate write.",
  run_in_background: true         // Teammates usually run in background
})

Characteristics:

• Joins team, appears in config.json
• Communicates via inbox messages
• Can claim tasks from shared task list
• Persists until shutdown
• Best for: parallel work, ongoing collaboration, pipeline stages

Key Difference

Aspect	Task (subagent)	Task + team_name + name (teammate)
Lifespan	Until task complete	Until shutdown requested
Communication	Return value	Inbox messages
Task access	None	Shared task list
Team membership	No	Yes
Coordination	One-off	Ongoing

---

Built-in Agent Types

These are always available without plugins:

Bash

Task({
  subagent_type: "Bash",
  description: "Run git commands",
  prompt: "Check git status and show recent commits"
})

• Tools: Bash only
• Model: Inherits from parent
• Best for: Git operations, command execution, system tasks

Explore

Task({
  subagent_type: "Explore",
  description: "Find API endpoints",
  prompt: "Find all API endpoints in this codebase. Be very thorough.",
  model: "haiku"  // Fast and cheap
})

• Tools: All read-only tools (no Edit, Write, NotebookEdit, Task)
• Model: Haiku (optimized for speed)
• Best for: Codebase exploration, file searches, code understanding
• Thoroughness levels: "quick", "medium", "very thorough"

Plan

Task({
  subagent_type: "Plan",
  description: "Design auth system",
  prompt: "Create an implementation plan for adding OAuth2 authentication"
})

• Tools: All read-only tools
• Model: Inherits from parent
• Best for: Architecture planning, implementation strategies

general-purpose

Task({
  subagent_type: "general-purpose",
  description: "Research and implement",
  prompt: "Research React Query best practices and implement caching for the user API"
})

• Tools: All tools (*)
• Model: Inherits from parent
• Best for: Multi-step tasks, research + action combinations

claude-code-guide

Task({
  subagent_type: "claude-code-guide",
  description: "Help with Claude Code",
  prompt: "How do I configure MCP servers?"
})

• Tools: Read-only + WebFetch + WebSearch
• Best for: Questions about Claude Code, Agent SDK, Anthropic API

statusline-setup

Task({
  subagent_type: "statusline-setup",
  description: "Configure status line",
  prompt: "Set up a status line showing git branch and node version"
})

• Tools: Read, Edit only
• Model: Sonnet
• Best for: Configuring Claude Code status line

---

Plugin Agent Types

From the compound-engineering plugin (examples):

Review Agents

// Security review
Task({
  subagent_type: "compound-engineering:review:security-sentinel",
  description: "Security audit",
  prompt: "Audit this PR for security vulnerabilities"
})

// Performance review
Task({
  subagent_type: "compound-engineering:review:performance-oracle",
  description: "Performance check",
  prompt: "Analyze this code for performance bottlenecks"
})

// Rails code review
Task({
  subagent_type: "compound-engineering:review:kieran-rails-reviewer",
  description: "Rails review",
  prompt: "Review this Rails code for best practices"
})

// Architecture review
Task({
  subagent_type: "compound-engineering:review:architecture-strategist",
  description: "Architecture review",
  prompt: "Review the system architecture of the authentication module"
})

// Code simplicity
Task({
  subagent_type: "compound-engineering:review:code-simplicity-reviewer",
  description: "Simplicity check",
  prompt: "Check if this implementation can be simplified"
})

All review agents from compound-engineering:

• agent-native-reviewer - Ensures features work for agents too
• architecture-strategist - Architectural compliance

---

Content truncated.