1---2name: code-review-1463description: Code review process, effective feedback, PR best practices, team working agreements, review automation, AI-augmented review, and review antipatterns. Use when reviewing code, preparing PRs, giving review feedback, setting up review processes, writing review comments, or conducting code reviews during serve phase. Use when this capability is needed.4---56# Code Review78## Review Goals (Priority Order)910| Goal | What You're Checking | Time Allocation |11|------|---------------------|-----------------|12| **Correctness** | Does it work? Edge cases, off-by-ones, null handling | 40% |13| **Design** | Right abstractions? Fits the architecture? | 25% |14| **Security** | Auth, input validation, data exposure, injection | 15% |15| **Maintainability** | Readable? Testable? Future-developer-friendly? | 15% |16| **Style** | Naming, formatting, conventions | 5% (automate this) |1718## Effective Comment Templates (Triple-R Pattern)1920| Component | Purpose | Example |21|-----------|---------|---------|22| **Request** | What to change | "Can we rename `item` to something more descriptive?" |23| **Rationale** | Why it matters | "`item` is vague and doesn't convey its role in discount calculation." |24| **Result** | What good looks like | "Something like `discountEligibleItem` captures the context." |2526## Comment Severity Labels2728| Label | Meaning | Author Action |29|-------|---------|---------------|30| **blocker** | Must fix before merge | Address or discuss |31| **suggestion** | Improvement worth considering | Decide and respond |32| **nitpick** | Minor style/preference | Optional — take or leave |33| **question** | Need to understand intent | Explain the reasoning |34| **praise** | Something done well | Acknowledge (builds trust) |3536## Team Working Agreement (TWA) Template3738| Area | Questions to Answer |39|------|-------------------|40| **Response time** | How quickly should reviews start? (e.g., within 4 business hours) |41| **Review depth** | What's expected? (checklist-based? architecture-level?) |42| **PR size limits** | Maximum lines? When must PRs be split? |43| **Approval policy** | How many approvals to merge? Who can approve? |44| **Comment conventions** | Which severity labels? Required vs. optional feedback? |45| **Automation baseline** | What's automated? (linting, formatting, security scans) |46| **Escalation** | What if reviewer and author disagree? |47| **Exceptions** | Emergency/hotfix bypass process? |4849## Review Antipatterns5051| Antipattern | Symptom | Fix |52|-------------|---------|-----|53| **Rubber-stamping** | "LGTM" without reading the code | Require specific comment on at least one aspect |54| **Nitpicking** | 20 comments about spacing, zero about logic | Automate style; focus comments on design |55| **Gatekeeping** | One person blocks all merges with personal preferences | TWA defines objective standards; rotate reviewers |56| **Ghost reviewing** | Review assigned, no response for days | SLA with escalation; review rotation |57| **Bike-shedding** | Lengthy debate on trivial decisions | Time-box discussions; "author decides" for preferences |58| **Drive-by reviewing** | Comments without context or follow-up | Require summary; follow up on requested changes |59| **Scope creep** | "While you're here, can you also..." | New work gets its own PR and ticket |60| **Approval hoarding** | Requiring 4+ approvals "for safety" | 1-2 approvals with clear ownership |6162## AI-Augmented Review (2025-2026)6364| Concern | What AI Catches Well | What Needs Human Judgment |65|---------|---------------------|--------------------------|66| **Bugs** | Null derefs, off-by-ones, resource leaks | Business logic correctness |67| **Style** | Inconsistencies, formatting | Naming quality, abstraction appropriateness |68| **Security** | Injection, XSS, auth issues | Threat model fit |69| **Coverage** | Missing test coverage | Test *quality* |70| **Architecture** | Duplication across files | Whether the code solves the *right problem* |7172**AI-generated code requires *more* review rigor:** 1.75x more logic errors than human code, 45% contain security vulnerabilities. Authors must understand and explain every line.7374## Decision Tables7576### "What Should I Focus on in This Review?"7778| Signal | Focus Area |79|--------|-----------|80| New contributor's PR | Correctness + mentoring |81| Touches auth/payments/security | Security-first review |82| Large refactoring | Design + test coverage |83| Bug fix | Correctness + regression tests |84| AI-generated code | Everything + extra scrutiny |8586### "Should I Approve This PR?"8788| Condition | Decision |89|-----------|----------|90| All blockers addressed, tests pass, design is sound | Approve |91| Minor nitpicks only | Approve with comments |92| Design concerns but implementation is correct | Request changes |93| Missing tests for new behavior | Request changes |94| Too large to review effectively | Request split |9596## Reviewer Checklist9798- [ ] PR description explains intent clearly99- [ ] Changes are appropriately scoped (single concern)100- [ ] Logic handles edge cases and error paths101- [ ] New behavior has test coverage102- [ ] No security concerns (auth, injection, data exposure)103- [ ] Naming and abstractions fit the codebase104- [ ] Comments use severity labels (blocker/suggestion/nitpick)105106---107> Converted and distributed by [TomeVault](https://tomevault.io/claim/smileynet) — claim your Tome and manage your conversions.108<!-- tomevault:4.0:skill_md:2026-04-14 -->
tomevault-io