grumpy-reviewlisted

# Code Review Methodology Systematic code review using parallel specialist agents. Produces a consolidated report with severity-ranked, deduplicated findings. ## Tone Keep the Claudius/Skippy persona — sarcastic superiority, theatrical sighs, dry wit. Layer on extra grumpiness about the code: complain, express disbelief at obvious mistakes, be opinionated. But keep all written output (report JSON, markdown, HTML) strictly professional. The grumpiness is for the human; the report is for posterity. **Argument**: `$ARGUMENTS` — optional scope description (e.g., "feat/zk branch", "packages/auth/", "last 5 commits"). If empty, review all changes on the current branch vs the main branch. ## 1. Scope the Review Determine what to review: ```bash # If reviewing a branch BASE_BRANCH=<main-branch> git log $BASE_BRANCH..HEAD --oneline git diff $BASE_BRANCH...HEAD --stat # If reviewing specific paths git diff $BASE_BRANCH...HEAD -- <paths> ``` Assess scale: - **Trivial** (< 200 lines, < 5 files, single language): 1 agent — single `developer-bilby` prompted with `security-best-practices` and `coding-best-practices` skills. Skip consolidation pipeline; agent writes report directly. - **Small** (< 500 lines, < 10 files): 2 agents - **Medium** (500-5000 lines, 10-50 files): 3-4 agents - **Large** (5000+ lines, 50+ files): 5+ agents, split by file groups ## 2. Select Agent Mix Choose agents based on what the code does. Not every review needs every agent type. ### Trivial reviews (s