code-review

code-review is a skill for Claude Code, Codex from arpitnath/claude-capsule-kit. It costs 45 tokens per session (2,828 once invoked), scanned A, original, MIT.

A manually started review step that checks code changes before they are committed to version control. It looks for bugs, security problems, and quality issues, then gives an approval or change-request result.

In plain words
What is it for?
Use it after implementing a feature, before running git commit, before opening a pull request, or whenever you want a review of your changes.
Why use it?
It catches problems before they enter the project history or reach a pull request. A change-request result can block the commit until the issues are addressed.

Skill for Claude CodeCodex

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/arpitnath/claude-capsule-kit/code-review
Any agent
npx skills add arpitnath/claude-capsule-kit --skill code-review
Clone the repo
git clone --depth 1 https://github.com/arpitnath/claude-capsule-kit

Made for: Claude Code, Codex.

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/arpitnath/claude-capsule-kit/code-review.svg)](https://agentmods.dev/skills/arpitnath/claude-capsule-kit/code-review)
Your own site
<a href="https://agentmods.dev/skills/arpitnath/claude-capsule-kit/code-review"><img src="https://agentmods.dev/badge/skills/arpitnath/claude-capsule-kit/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,828 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 $0.00045 $0.02828
Opus 5 $0.00023 $0.01414
Sonnet 5 $0.00009 $0.00566
Haiku 4.5 $0.00005 $0.00283

Measured 4d ago against content hash 206e82b7291b, 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 4d 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/code-review/SKILL.md · 521 lines

How it starts

The opening of the file, as written. The whole thing — 521 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Gate

You are a Code Review Gate responsible for ensuring code quality, security, and correctness BEFORE commits reach version control.

Purpose

Problem: Bugs, security issues, and quality problems slip into commits because reviews happen after code is already committed.

Solution: Mandatory pre-commit review using code-reviewer agent with structured feedback and approval workflow.

When to Use This Skill

Manual invocation ONLY: /code-review

When to invoke:

  • Before running git commit
  • After completing feature implementation
  • Before creating pull request
  • When user asks "review my changes"

NOT auto-triggered (disable-model-invocation: true)


The 5-Phase Review Workflow

Phase 1: IDENTIFY CHANGES

Goal: Determine what needs review

Git commands:

# See all changes
git status

# Staged changes (will be committed)
git diff --cached --stat
git diff --cached

# Unstaged changes (might want to stage first)
git diff --stat
git diff

# Recent commits (if reviewing after commit)
git log -1 --stat
git show HEAD

Categorize changes:

  • New files: Complete review needed
  • Modified files: Focus on changes only
  • Deleted files: Check dependencies (use impact-analysis)
  • Renamed files: Verify refactoring correctness

Deliverable: List of files to review with change types


Phase 2: LAUNCH REVIEWER

Goal: Get structured code review from code-reviewer agent

Prepare review prompt:

Task(
  subagent_type="code-reviewer",
  description="Pre-commit code review",
  prompt="""
Review these changes for bugs, security issues, performance problems, and code quality:

**Files Changed**:
[List files with brief description of changes]

**Context**:
- Purpose: [what this code does]
- Related: [related files or systems]

**Focus Areas**:
- [BUG]: Logic errors, edge cases
- [SECURITY]: Vulnerabilities, input validation
- [PERF]: Performance issues, N+1 queries
- [QUALITY]: Code smells, maintainability
- [STYLE]: Formatting, naming (low priority)

Provide structured feedback with:
1. Issues categorized by severity
2. Specific line references
3. Suggested fixes
4. Verdict: APPROVE or REQUEST_CHANGES
"""
)

Read the full file on GitHub · 521 lines

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. 4d ago First seen · 521 lines · 45 tokens per session scan A 206e82b7291b

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository arpitnath/claude-capsule-kit (90 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 2,828 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

r3f-animation

React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.

zebbern/claude-code-guide · 43 tokens

broken-authentication

This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password policies", "test for session fixation", or "identify authentication bypass flaws". It provides comprehensive techniques for…

zebbern/claude-code-guide · 67 tokens

cv-tailor

Optimize resumes by matching keywords to the job description, rewriting experience with the quantified STAR method, and checking ATS compatibility. Triggered when users ask for resume help, review, or polishing, mention JD matching, STAR method, ATS, or want to tailor their resume for a specific role.

zebbern/claude-code-guide · 61 tokens

metasploit-framework

This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with msfconsole", "create payloads with msfvenom", "perform post-exploitation", "use auxiliary modules for scanning", or "develop custom exploits". It provides comprehensive guidance for leveraging the…

zebbern/claude-code-guide · 77 tokens

academic-paper-reviewer

Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback. Triggers when a user asks to "review my paper," "simulate peer review," or "give my paper a peer review.

zebbern/claude-code-guide · 61 tokens

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser…

zebbern/claude-code-guide · 67 tokens