subagent-driven-development

Read the plan once, extract all tasks with full text into a TodoWrite list, then dispatch one implementer subagent per task with the complete task text and context. After each task, run a spec compliance review followed by a code quality review before marking it complete.

Subagent-driven development runs in the same session with a fresh subagent per task and automatic two-stage reviews, enabling faster iteration. Executing plans uses a parallel session with human-in-the-loop handoffs between tasks.

Avoid it when tasks are tightly coupled and cannot be implemented independently, when no written implementation plan exists yet, or when you intend to execute the plan in a separate parallel session instead of the current one.

No. Dispatching multiple implementation subagents in parallel causes conflicts between their changes. Tasks must be implemented sequentially, with each task passing both review stages before the next begins.

The same implementer subagent fixes the reported issues, then the reviewer reviews again. This loop repeats until approval, and the code quality review only starts after spec compliance passes.