# Better Code Review

> Risk-first semantic code review focused on correctness, security, regressions, and missing tests with severity-ordered findings.

- Skill: `rldyourmnd/better-code-review` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add rldyourmnd/better-code-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rldyourmnd/better-code-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: rldyourmnd (https://skillmd.com/u/rldyourmnd)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rldyourmnd/better-code-review

---


# Better Code Review (Codex)

Use this skill for high-quality, evidence-based code review.

## Trigger

Use when the user asks to:
- review local changes, commits, or branch diffs,
- find bugs/regressions/security risks,
- validate release readiness,
- identify test coverage gaps.

## Primary Workflow

1. Determine review scope (diff/files/branch).
2. Analyze changed symbols and impacted references.
3. Validate behavior, contracts, and failure handling.
4. Identify missing tests and risky assumptions.
5. Report findings ordered by severity.

## Operating Rules

- Findings first, summary second.
- Include file references and concrete impact.
- Avoid style-only noise unless it affects behavior.
- No code edits unless user explicitly requests fixes.

## Output Contract

- `Findings` (severity-ordered)
- `Open questions`
- `Residual risks`
- `Readiness verdict`