Review Lens

Code review with anti-hallucination diff annotation and confidence-scored findings, in two modes — a fast walkthrough-plus-findings pass by default, or a multi-material fan-out on demand. Runs before a pull request: the report goes to the chat, with optional fix application and a saved report.

Triggers

• Quick review (default — "review", "review my changes", "check my diff", "review against main") → run the workflow below
• Deep review ("deep review", "full review", "thorough review") → run it in deep mode
• Re-review ("re-review", "check fixes", "are the issues resolved") → run it against the prior findings

Workflow

Start immediately when triggered. No confirmation needed to begin.

1. Load common.md — the diff annotation algorithm, the size gate, the confidence rubric, what not to report, the output template, the fix-suggestion rules, and the data trust boundary. Both modes apply it in full.
2. Set up. Run git status --porcelain: review the working directory when it has uncommitted changes, otherwise compare the current branch against the base the user names, else main. Capture the diff and changed files, annotate every added line with its [L<n>] marker, and apply the size gate before going further.
3. Pick the mode. Default to quick and load quick-review.md. Load deep-review.md only when the user asks for depth or the change is risky or wide-reaching — it fans out by material, at higher cost.
4. Load guidelines-audit.md for the guideline-compliance portion, whichever mode ran.
5. Assemble and output. Render the loaded template, sorted by severity. On a re-review, mark each prior finding fixed, persisting, or regressed and output the status table first. Print to the terminal, offer to save CODE_REVIEW.md, then offer to apply the suggested fixes.