subagent-driven-development

To automate task dispatch for development plans, this Skill coordinates fresh independent subagents to execute isolated tasks within the same session, ensuring context pollution is avoided. It allocates a new subagent per task for rapid outcomes.

A two-stage review process enforces spec compliance first, then evaluates code quality for each task completed by an implementer subagent. This structured workflow ensures automated completion signaling after iterative improvements.

You can execute independent implementation tasks without context pollution by orchestrating fresh subagents per task. This approach dispatches a new isolated subagent for each action, preventing cross-task interference within the same session.

Yes, you can use subagent orchestration for complex plan execution within a single session. The system handles per-task questions, self-reviews, and iterative improvements, making it suitable for managing structured multi-task workflows.

You should not use fresh subagents for task dispatch when tasks are highly interdependent rather than mostly independent. The system is designed for isolated execution and a structured two-stage review process, which may not suit tightly coupled workflows.