orchestration-patterns

Orchestration Patterns

Experimental: Agent teams are disabled by default. Enable with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS in your settings.json or environment.

Proven patterns for structuring agent teams. Choose the right pattern based on your task's coordination needs.

Related skills:

• Orchestrating - Primitives overview and quick reference
• Team Management - Team lifecycle tools
• Task System - Task creation and dependencies
• Messaging - Inter-agent communication
• Agent Types - Choosing the right agent for each role

See also: Complete Workflows for full end-to-end examples.

---

Pattern Selection Guide

Pattern	When to Use	Coordination	Dependencies
Parallel Specialists	Multiple independent reviews	Low	None
Pipeline	Sequential stages	Medium	Linear chain
Swarm	Many similar independent tasks	Low	None
Research + Implementation	Learn then build	Low	Phase gate
Plan Approval	High-risk changes	High	Approval gate
Multi-File Refactoring	Cross-file changes	Medium	Fan-in
RLM (Recursive Language Model)	Files exceeding context limits	Medium	Fan-out/fan-in

---

Pattern 1: Parallel Specialists

Multiple specialists review code simultaneously, each with a different lens:

// 1. Create team
TeamCreate({ team_name: "code-review", description: "Parallel code review" })

// 2. Spawn specialists in parallel (single message, multiple Task calls)
Task({
  team_name: "code-review",
  name: "security",
  subagent_type: "sdlc:security-reviewer",
  prompt: "Review the PR for security vulnerabilities. Focus on: SQL injection, XSS, auth bypass. Send findings to team-lead.",
  run_in_background: true
})

Task({
  team_name: "code-review",
  name: "quality",
  subagent_type: "feature-dev:code-reviewer",
  prompt: "Review the PR for bugs, logic errors, and performance issues. Focus on: N+1 queries, memory leaks, slow algorithms. Send findings to team-lead.",
  run_in_background: true
})

Task({
  team_name: "code-review",
  name: "simplicity",
  subagent_type: "code-simplifier:code-simplifier",
  prompt: "Review the PR for unnecessary complexity. Focus on: over-engineering, premature abstraction, YAGNI violations. Send findings to team-lead.",
  run_in_background: true
})

// 3. Wait for results (messages arrive automatically)
// 4. Synthesize findings and cleanup
SendMessage({ to: "security", message: { type: "shutdown_request", reason: "Done" } })
SendMessage({ to: "quality", message: { type: "shutdown_request", reason: "Done" } })
SendMessage({ to: "simplicity", message: { type: "shutdown_request", reason: "Done" } })
// Wait for approvals...
TeamDelete()