What problem does it solve? Executing a multi-task implementation plan in one AI session often leads to context pollution, skipped reviews, and lost progress after context compaction. This Skill orchestrates plan execution by delegating each task to a fresh subagent with isolated context, enforcing per-task reviews, and tracking progress in a persistent ledger. ## Core Features & Use Cases - Fresh subagent per task: Dispatches an implementer subagent with a task brief file, then a task reviewer subagent that verifies spec compliance and code quality against the diff. - Bounded fix loop with escalation: Runs up to five fix rounds per task, resuming the original implementer for rounds 1-3 and escalating to a more capable model for rounds 4-5, with adjudication at the cap. - Ledger-based recovery: Records task completions, rulings, and parked findings in a per-plan workspace ledger so progress survives context compaction. - Use Case: Given a plan file with ten independent tasks, the controller dispatches implementers one at a time, reviews each diff via generated review packages, and finishes with a whole-branch review before merging. ## Quick Start Use subagent-driven development to execute the implementation plan at docs/plans/feature-plan.md task by task with reviews.
