subagent-driven-developmentlisted

# Subagent-Driven Development Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and two gates at the end: a task-by-task conformance audit, then a broad whole-branch review. **Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work. **Core principle:** Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration **Narration:** between tool calls, narrate at most one short line — the ledger and the tool results carry the record. **When you do escalate to your human partner** — the plan is wrong, an iteration cap was hit, residuals were parked — use the shape below. A subagent's report to you is unchanged; that is machine to machine. **Escalation shape** (detail and a worked example: [escalation-format.md](../using-superpowers/references/escalation-format.md)): 1. **What breaks or costs** if nothing is decided — one sentence, the consequence and not the mechanism. 2. **2–4 options with the cost of each**, always including doing nothing now. 3. **A recommendation naming which source backs it** — a project pattern at `file:line`, the dependency's official docs, or g