multi-agent-orchestrationlisted

# Multi-Agent Orchestration Execute work through subagents instead of a single context. Two modes: **parallel dispatch** (independent tasks to concurrent isolated-context agents) and **plan-driven execution** (a plan as a sequence of implementer-subagents, each reviewed before the next). Use when the work exceeds one context window, or when isolation prevents cross-task contamination. ## When to use - A plan/ticket set is too large for one session — drive it as sequenced implementer-subagents - 2+ independent tasks that don't share state — dispatch them concurrently to isolated contexts - A task needs a fresh context to avoid prior-session bias or context bloat - Reviewing one task's output before starting the next (plan-driven checkpoint) - Triggers on "parallel agents", "subagent execution", "dispatch tasks", "fan out", "并行 agent", "子代理执行", "派发任务" **Not for:** breaking a plan into tickets (use `breakdown` — this skill *executes* the tickets, it doesn't decompose them); doing the implementation yourself in one context (use `implement`); single-task work that fits one session (just do it — orchestration has overhead). ## Steps ### 1. Decide: parallel dispatch or plan-driven execution? - **Parallel dispatch** — the tasks are independent (no data dependency between them). Run them concurrently. Use when: lint-fixing N files, researching N competitors, generating N independent components. - **Plan-driven execution** — the tasks have an order (each informs or gates the nex