What problem does it solve? Executing a multi-task implementation plan in one session risks context pollution, skipped verification, and lost progress after compaction. This Skill orchestrates plan execution by delegating each task to an isolated subagent, gating every task behind a spec-compliance and code-quality review, and tracking progress in a persistent ledger. ## Core Features & Use Cases - Fresh subagent per task: Dispatch implementer subagents with task briefs extracted to files, keeping the controller's context clean for coordination. - Structured review loop: Run a task reviewer after each task, a bounded five-round fix loop with scoped re-reviews, and a final whole-branch review on the most capable model. - Ledger-based recovery: Track completions, fix rounds, and parked findings in a per-plan workspace ledger so progress survives context compaction. - Use Case: Given a written implementation plan with eight independent tasks, execute all of them in the current session: each task is implemented, tested, reviewed, and committed by subagents, ending with a clean final review before finishing the branch. ## Quick Start Use subagent-driven development to execute the implementation plan at docs/plans/feature-plan.md task by task with reviews.
