subagent-driven-development

To execute an implementation plan task by task, this Skill dispatches a fresh, independent subagent for each task, ensuring focused context without pollution. It enforces TDD principles and uses a two-stage review process—spec compliance then code quality—after each task's completion within a single continuous development session.

Subagent-driven development is an AI development approach where code generation is handled by dispatching independent subagents for each task. It prevents context pollution by using a fresh agent per task, followed by a two-stage review process to ensure spec compliance and code quality.

Yes, you can automate agile development tasks by using this Skill to break down implementation plans into independent tasks like creating API endpoints or writing unit tests. Each task is executed by a fresh subagent, reviewed for spec compliance and code quality, and iteratively fixed.

The two-stage code review process for AI-generated code first checks spec compliance, then evaluates code quality after a task's completion. If issues are found, subagents iteratively fix them, and re-reviews ensure resolution before moving to the next task in the development session.

Assigning a new AI agent to each development task prevents context pollution and ensures strict focus on the specific task. This task isolation, combined with iterative fixes and TDD principles, maintains code quality throughout a continuous development session.