Skip to content

rn-code-reviewer

The reviewer agent checks implemented code for real issues with high precision. It uses confidence-based scoring to report only findings that truly matter, filtering out noise and false positives.

PropertyValue
ModelSonnet
ColorMagenta
Skillsrn-testing, rn-best-practices
ToolsGlob, Grep, LS, Read

The reviewer is read-only. It analyzes code but does not modify it.

  • “review the code I just wrote for the profile edit screen”
  • “check these files for any React Native specific issues before I merge”
  • Phase 6 of the rn-feature-dev pipeline (3 reviewer agents check different aspects)

Each potential issue is rated 0-100:

ScoreMeaning
0False positive or pre-existing
25Might be real, could be false positive
50Real but minor or unlikely in practice
75Verified real issue, will impact functionality
100Confirmed definite issue, will happen frequently

Only issues with confidence >= 80 are reported.

  • Logic errors and undefined access paths
  • Null/undefined handling in component props and state
  • Race conditions in async operations (fetch + setState after unmount)
  • Missing error boundaries around async data screens
  • Memory leaks (uncleared intervals, uncancelled subscriptions)
ConventionPriority
testID coverage on all interactive elementsCritical
__DEV__ guards on all dev-only codeCritical
Zustand stores registered in __ZUSTAND_STORES__Important
Selector memoization (no inline .filter/.map)Important
Navigation param typingImportant
Fast Refresh safety (no module-scope side effects)Important
No bare console.log in production pathsImportant
  • File naming matches existing patterns
  • Folder placement follows project structure
  • Import style matches (relative vs alias)
  • CLAUDE.md rules respected
  • No duplicate code that could use existing utilities

Applies all 46 rules from the best practices skill. Reads the full reference file for any rule category detected in the code under review.

Scanning order:

  1. CRITICAL (always check): falsy && [RN-1.1], bare strings [RN-1.2], inline components [RN-16.1]
  2. HIGH (when keyword triggers match): list performance, animation GPU, scroll, navigation
  3. MEDIUM (when keyword triggers match): state, compiler, UI, design system
  4. LOW (only if 3+ occurrences AND confidence >= 80): monorepo, deps, JS, fonts

Groups findings by severity:

Critical (confidence >= 90): clear description, file path, line number, concrete fix suggestion.

Important (confidence >= 80): same format as Critical.

If no high-confidence issues are found, confirms the code meets standards with a brief summary.