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 coordinates the whole run: a fresh implementer subagent per task, a spec-and-quality review after each task, a bounded fix loop, and a final whole-branch review, with a ledger file tracking every decision. ## Core Features & Use Cases - Per-task subagent dispatch: Each task gets a fresh implementer with a brief file, a report file, and explicit model selection, keeping the controller's context clean for coordination. - Two-stage review pipeline: A task reviewer checks spec compliance and code quality per task; a final whole-branch reviewer audits the complete diff before merge. - Bounded fix loop with adjudication: Up to five fix rounds per task with scoped re-reviews; unresolved findings are ruled on and recorded in the ledger rather than silently dropped. - Use Case: You have a written implementation plan with eight tasks. Run this Skill to execute every task autonomously, reviewing and fixing each diff, and finish with a clean reviewed branch plus a rulings report. ## Quick Start Ask your agent to use subagent-driven development to execute the implementation plan at docs/plans/feature-plan.md.
