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. Follow each implementation with 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 under- or over-building. The second stage reviews code quality including conventions, error handling, test coverage, and security. Spec review must pass before quality review begins.

Fresh subagents prevent context pollution from accumulated state, giving each task clean, focused context without confusion from prior tasks' code or reasoning. This improves consistency and makes review outcomes more reliable across all tasks.

Avoid it when tasks touch the same files and cannot run independently, when no implementation plan exists, or when tasks are too large. Each task should be 2-5 minutes of focused work, such as creating one model or one endpoint.

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.

Every implementer subagent context includes TDD instructions: write a failing test first, verify it fails, write minimal implementation, verify it passes, run the full suite for regressions, then commit. This ensures each task lands with test coverage.