Subagent-Driven Development

Execute a plan by dispatching a fresh subagent or parallel worker per task, if your client supports one, with two-stage review after each: specification compliance first, then code quality. If the client has no worker capability, use executing-plans and do the tasks and review passes in sequence.

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 + two-stage review (spec then quality) = high quality, fast iteration