code-review

code-review is a skill for Claude Code, Codex from int2t05/engineering-skills. It costs 112 tokens per session (2,175 once invoked), scanned A, original, MIT.

A structured way to examine code changes before or during a merge. It checks both the project's coding standards and whether the change matches its requested behavior.

In plain words
What is it for?
Use it before merging a change, while making a difficult implementation decision, before declaring work complete, or when assessing review feedback.
Why use it?
It helps find missed requirements, design problems, and unsupported claims that automated checks may not catch.

Skill for Claude CodeCodex

Part of the engineering-skills plugin — 47 skills, 1 agent, 1 hook shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/int2t05/engineering-skills/code-review
Any agent
npx skills add int2t05/engineering-skills --skill code-review
Clone the repo
git clone --depth 1 https://github.com/int2t05/engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 47 skills, 1 agent, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/int2t05/engineering-skills/code-review.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/code-review)
Your own site
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/code-review"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00112 $0.02175
Opus 5 $0.00056 $0.01087
Sonnet 5 $0.00022 $0.00435
Haiku 4.5 $0.00011 $0.00217

Measured 3d ago against content hash 1f1da23352d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/07-verify/code-review/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Four review modes, each a different moment and posture. Pick by when the review happens and who's giving vs receiving it.

When to use

  • pre-merge (default) — before merging a PR/change: two-axis review, Standards (repo conventions + smell baseline) and Spec (faithful to the originating issue/spec)
  • in-flight — during implementation, before a decision stands: adversarial cross-examination biased to disprove, not approve
  • evidence-gate — before claiming a task done/fixed/passing: produce fresh verification evidence, not assertion
  • receiving — when review feedback arrives: verify the feedback is correct before acting on it; technical rigor over performative agreement
  • Triggers on "review this", "code review", "before merge", "代码审查", "合并前审查", "帮我看看这代码", "能合并吗", "are you sure", "verify before done", "收到评审意见"

Not for: deep security review (use security-review); machine-detectable lint/style (use linting); runtime behavior bugs (use debugging).

Steps

1. Pick the mode

  • Merging a PR / evaluating a diff → pre-merge (Step 2)
  • Mid-implementation, a non-trivial decision is about to stand → in-flight (load references/review-modes.md §in-flight)
  • About to claim "done" / "fixed" / "passing" → evidence-gate (load references/review-modes.md §evidence-gate)
  • Review feedback just arrived and you're deciding whether to act on it → receiving (load references/review-modes.md §receiving)

2. Pre-merge review (default mode)

2a. Pin the fixed point + gather sources

Capture the diff once: git diff <fixed-point>...HEAD (three-dot, against the merge-base). Confirm the ref resolves (git rev-parse <fixed-point>) and the diff is non-empty before going further.

Identify, in order:

  • Spec source — issue refs in commit messages (#123, Closes #45), a user-supplied path, or a spec under docs//specs/. If none found, ask; if there isn't one, the Spec axis reports "no spec available".
  • Standards sources — anything documenting how code should be written (CODING_STANDARDS.md, CONTRIBUTING.md, lint configs). On top of repo docs, the Standards axis always carries the smell baseline below.

Read the full file on GitHub · 130 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 130 lines · 112 tokens per session scan A 1f1da23352d3

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 15d ago), licensed MIT. It adds 112 tokens to every session and 2,175 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.