subagent-driven-development

Read the plan file once, extract all tasks into a todo list, then dispatch a fresh implementer subagent per task with the full task text in context. After each implementation, run a spec compliance review and a code quality review before marking the task complete.

The first stage checks spec compliance against the original task requirements, catching missing features or scope creep. The second stage reviews code quality including conventions, error handling, test coverage, and security. Spec compliance must pass before quality review begins.

A fresh subagent per task prevents context pollution from accumulated state, giving each task clean, focused context. This avoids confusion from prior tasks' code and reasoning, and keeps quality checks consistent across all tasks.

The implementer subagent, or a new fix subagent, addresses the specific issues, then the reviewer re-reviews the work. This loop repeats until approval, and the workflow never proceeds to the next task with open critical or important issues.

Avoid it when tasks are tightly coupled and touch the same files, since parallel or sequential subagents would conflict. It also adds overhead for trivial single-step changes where direct implementation is faster than dispatching implementer plus two reviewers.