multi-agent-orchestrationlisted

# Multi-Agent Orchestration Coordinate multiple specialized agents for complex tasks. ## When Claude Code is the Orchestrator If Claude Code itself is fanning out (not your user's application code), **emit multiple `Agent` tool calls in a single response message** — do not serialize. Opus 4.7 is conservative about parallel delegation and will run agents sequentially unless explicitly instructed otherwise. The code patterns below (asyncio.gather, etc.) describe application-level fan-out; when Claude is the orchestrator, the equivalent is: call `Agent` N times in one tool-use block, then synthesize after all return. Canonical example: `plugins/engineering-toolkit/skills/brainstorming/references/deep-mode-phases.md` ("Launch ALL 8 agents in ONE message"). ## Fan-Out/Fan-In Pattern (Application Code) ```python async def multi_agent_analysis(content: str) -> dict: """Fan-out to specialists, fan-in to synthesize.""" agents = [ ("security", security_agent), ("performance", performance_agent), ("code_quality", quality_agent), ("architecture", architecture_agent), ] # Fan-out: Run all agents in parallel tasks = [agent(content) for _, agent in agents] results = await asyncio.gather(*tasks, return_exceptions=True) # Filter successful results findings = [ {"agent": name, "result": result} for (name, _), result in zip(agents, results) if not isinstance(result, Exception) ] # Fan-in: Sy