# Eng Code Review Playbook

> Review changes for correctness, safety, and regressions. Use when this capability is needed.

- Skill: `tomevault-io/eng-code-review-playbook` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add tomevault-io/eng-code-review-playbook`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/eng-code-review-playbook/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tomevault-io (https://skillmd.com/u/tomevault-io)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tomevault-io/eng-code-review-playbook

---


# Code Review Playbook

## Repo anchors (autocodex)
- INTERNAL_PATH: `internal/`
- DOCS_PATH: `docs/`

## When to use
- Reviewing PRs or local diffs before merge.

## Preconditions
- You can see the diff and tests run.

## Inputs to confirm
- Intended behavior change
- Test evidence

## Required artifacts
- Findings list ordered by severity
- Open questions
- Short summary

## Quick path
- Scan for correctness, then safety, then tests.

## Steps
1) Identify behavior changes and edge cases.
2) Verify observability and error handling.
3) Check tests and docs.

## Failure modes and responses
- **No tests**: flag as blocking.
- **Hidden behavior changes**: request clarification.

## Definition of done
- Findings are clear, actionable, and prioritized.

## Example (minimal)
- **Finding**: Missing error handling in plugin handshake.

---
> Converted and distributed by [TomeVault](https://tomevault.io/claim/oodaris) — claim your Tome and manage your conversions.
<!-- tomevault:4.0:skill_md:2026-04-11 -->