What problem does it solve? Executing a multi-task implementation plan in one session risks context pollution, skipped reviews, and lost progress after compaction. This Skill orchestrates plan execution by dispatching a fresh implementer subagent per task, a task reviewer after each, and a final whole-branch review, with a durable progress ledger for recovery. ## Core Features & Use Cases - Per-task subagent dispatch: Each task gets a fresh Codex or Claude implementer with a file-based task brief, keeping the controller's context clean. - Two-gate review loop: Every task passes spec-compliance and code-quality review by a Claude reviewer reading a generated diff package, with fix cycles for Critical/Important findings. - Durable progress ledger: Completed tasks are recorded in a git-ignored ledger file so work is never re-dispatched after context compaction. - Use Case: You have a 6-task implementation plan from a planning session. This Skill extracts each task brief to a file, dispatches Codex implementers with tiered model selection, reviews each diff, and finishes with a whole-branch review before merge. ## Quick Start Use subagent-driven development to execute the implementation plan in docs/plans/feature-plan.md task by task with review after each task.
