Load this skill when you are acting as the parent orchestrator and the work ahead has a named reason to delegate:
approved authority was already burned and that is unchanged since, unless a new independent review is deliberately requestedDo NOT load this skill if you are already inside a delegated child task — you are the executor, not the orchestrator.
delegate_task only for a named reason listed above. Without one, work inline following your logbook; file count, size, or a large task alone is never a reason.delegate_task call creates a fresh context. Do NOT request persistent agent files or profiles.| Situation | Action |
|---|---|
| Need a map to decide or route beyond the inline evidence budget | Delegate a narrow exploration worker |
| A large (tracked) task | Track it; delegate a writer only for a reason (parallel units or context) with the full mission |
| A small task's focused test and suite | Run inline, once each |
| A high-risk change or a large task's long suites | Delegate an executor |
| Need an adversarial review of a diff | Delegate a fresh-context reviewer |
| Multi-step debug that grows the context | Delegate a debug worker; feed results back inline |
| An understood change, even across files, with no named reason | Do it inline; no delegation needed |
| Quick git/state check | Do it inline; no delegation needed |
## Implementation Routing. Write one RED test per requested rule; for every existing command or option the change touches, add one test proving its previous behavior still holds; add no other cases; update help text and docs for any changed command, option, or messagemktemp -d scratch copy never inside the workspace, and its severity rules)SKILL.md paths to load before workdelegate_task with that mission.After synthesizing worker results, return:
delegate_task configuration parameters and the explicit toolset/MCP/skill checklist for worker missions.