What problem does it solve? It catches bugs, architecture flaws, and requirement gaps early by having a dedicated reviewer subagent examine your completed work before issues compound or code reaches main. ## Core Features & Use Cases - Structured Review Dispatch: Sends a code-reviewer subagent a curated context (what was implemented, requirements, git SHA range) instead of your full conversation history. - Severity-Triaged Feedback: Returns findings classified as Critical, Important, or Minor with file:line references and fix guidance. - Workflow Integration: Fits subagent-driven development (review after each task), plan execution (review every batch), and ad-hoc work (review before merging). - Use Case: After finishing a feature task, you capture the base and head git SHAs, dispatch the reviewer with the plan reference, receive an assessment like "mergeable after fixes", address the Important issues, and continue to the next task. ## Quick Start Ask the AI to request a code review of your just-completed task using the git range from the previous commit to HEAD before continuing.