dispatching-subagentslisted

# Dispatching Subagents ## Overview **Core principle:** Delegate to go faster and to keep your own context clean — but treat the host as a **budget**, not an infinite pool. The goal is *lower wall-clock*, not *maximum concurrency*. Ten agents that make the machine swap are slower than three that don't. First check the authority and capability boundary. This skill never grants permission to spawn an agent. If the host or active instructions forbid subagents, use batched read-only tool calls where available or execute the same dependency order serially. Two wins from delegating, and they're different: - **Parallelism** — independent work runs at once, so wall-clock ≈ the slowest chain, not the sum. - **Context hygiene** — a subagent reads the haystack and hands you the needle; the file dumps never enter your context. Reach for this even when you *don't* need speed. ## Reach for a Subagent When Only after the host permits subagents: - **Fan-out search / exploration** — "where is X handled", sweeping many files or naming conventions. Delegate; keep the conclusion, not the excerpts. - **Independent tasks** — spikes of two rival approaches, reviewing N files, building M targets — anything with no ordering dependency between the pieces. - **Adversarial verification** — spawn independent skeptics to try to *refute* a claim (behavior unchanged? bug real?). Diverse lenses catch what one pass misses. - **Anything that would flood your context** with output you won't keep. ##