What problem does it solve? Executing a multi-task implementation plan in a single AI session leads to context pollution, skipped reviews, and inconsistent quality. This Skill orchestrates plan execution by dispatching a fresh subagent per task and enforcing spec compliance and code quality reviews after each one. ## Core Features & Use Cases - Fresh Subagent Per Task: Each task runs in an isolated context with curated instructions, preventing cross-task confusion and preserving the controller's context. - Two-Stage Review Gates: Every task passes a spec compliance review first, then a code quality review, with fix-and-re-review loops until approved. - Status-Based Escalation: Implementer subagents report DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, or BLOCKED, and the controller responds with more context, a more capable model, or task decomposition. - Use Case: You have a written plan with 5 independent tasks. The controller extracts all tasks, dispatches an implementer subagent for each, runs both reviews per task, and finishes with a final whole-implementation code review before merging the branch. ## Quick Start Use subagent-driven development to execute the implementation plan at docs/plans/feature-plan.md task by task with reviews.
