What problem does it solve? After non-trivial code edits, developers need a reliable second-model review before committing or shipping, but manually bundling diffs, invoking reviewer CLIs, and validating their output is repetitive and error-prone. ## Core Features & Use Cases - Structured Review Helper: Bundles local, branch, or commit diffs and invokes a selected review engine (Codex, Claude, Droid, or Copilot) with validated structured output and clear exit codes. - Review Panels: Runs multiple reviewers against one frozen bundle with per-engine model and thinking/effort settings for higher-risk changes. - Parallel Closeout: Runs focused tests in parallel with the review, with guidance to rerun both until no accepted or actionable findings remain. - Use Case: After fixing a PR branch, run the helper with --mode branch --base origin/main to get a Codex review, verify each finding against the real code, fix accepted issues, and rerun until the helper reports a clean result. ## Quick Start Ask the assistant to run an autoreview on the current branch against origin/main using the default Codex engine and report any accepted findings.
