spawn-checklistlisted

# Spawn Checklist Run before every `Agent()` call. Spawning is the dominant token cost — every subagent rebuilds its context cache from scratch, and that cache-creation, not model output, is the bulk of the bill. The cheapest work is the spawn that never happens. Cheap enough to reload before each spawn. Reload it. ## Pre-Spawn Checklist 1. **Total scope size** — sum the estimated diff/output across the whole batch, not per item. Under ~100 lines total: fold into an existing or sibling agent via `SendMessage`; do not spawn. 2. **Genuine parallelism** — is there a real wall-clock or file-independence need, or would sequential work merely take "a bit longer"? No real need → one agent, sequential. 3. **Reuse** — is an agent already live in the same file/domain scope? → `SendMessage` it. Accumulated context beats a cold spawn (see § Agent Reuse in `grand-admiral`). 4. **Model tier** — set explicitly on this spawn per the table below. Never leave it to the agent's frontmatter fallback. 5. **Worktree** — for code-mutating agents: pre-create it and inject the resolved SHA. Never rely on `isolation: "worktree"` alone (see § Worktree Isolation in `grand-admiral`). 6. **Monitoring** — is the stall watchdog Monitor running for this session? An un-monitored dispatch is a doctrine violation (see § Recovery in `grand-admiral`). **Anti-pattern — file-independence is not spawn-justification.** A real case: four doc-only fixes, each under 20 lines, each in its own file, got four separate