code-review-checklist

code-review-checklist is a skill for Claude Code from curiositech/some_claude_skills. It costs 50 tokens per session (545 once invoked), scanned A, original, MIT.

A tool that turns a pull request's code changes into a review checklist tailored to the programming language, project patterns, and kind of change.

In plain words
What is it for?
Use it before reviewing a feature, bug fix, or refactor to check areas such as security, performance, readability, input handling, and authentication.
Why use it?
It helps reviewers know what to inspect and keeps reviews consistent, especially in unfamiliar parts of a codebase.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the code-review-checklist plugin — 1 skill shipped together

Good fit Use it before reviewing a feature, bug fix, or refactor to check areas such as security, performance, readability, input handling, and authentication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curiositech/some_claude_skills/code-review-checklist
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.

Any agent
npx skills add curiositech/some_claude_skills --skill code-review-checklist
Clone the repo
git clone --depth 1 https://github.com/curiositech/some_claude_skills

Made for: Claude Code.

Or install code-review-checklist, the plugin that ships this one along with the rest of its 1 skill.

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-checklist

README.md
[![agentmods](https://agentmods.dev/badge/skills/curiositech/some_claude_skills/code-review-checklist/github.svg)](https://agentmods.dev/skills/curiositech/some_claude_skills/code-review-checklist)
Your own site
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/code-review-checklist"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/code-review-checklist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-review-checklist

Your own site · 80×15
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/code-review-checklist"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/code-review-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00050 $0.00545
Opus 5 $0.00025 $0.00272
Sonnet 5 $0.00010 $0.00109
Haiku 4.5 $0.00005 $0.00055

Measured 9d ago against content hash d2b69e965dc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-review-checklist 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 9d 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.

.claude/skills/code-review-checklist/SKILL.md · 73 lines

What it actually says

Code Review Checklist Generator

Generate thorough, contextual code review checklists that help reviewers focus on what matters most for each specific PR.

When to Use

  • Before starting a code review to know what to look for
  • When onboarding new team members to review standards
  • To ensure consistent review quality across the team
  • When reviewing unfamiliar parts of the codebase

Approach

  1. Analyze the Diff: Understand what files changed and the nature of changes
  2. Identify Patterns: Detect the type of change (feature, bugfix, refactor, etc.)
  3. Language-Specific Checks: Apply relevant checks for the programming language
  4. Project Context: Consider existing patterns and conventions in the codebase
  5. Generate Checklist: Produce prioritized, actionable review items

Checklist Categories

Security

  • Input validation present
  • No hardcoded secrets or credentials
  • Proper authentication/authorization checks
  • SQL injection prevention
  • XSS prevention for web code

Performance

  • No N+1 query patterns
  • Appropriate caching considered
  • No unnecessary loops or iterations
  • Efficient data structures used

Maintainability

  • Code is readable and self-documenting
  • Functions are appropriately sized
  • No code duplication
  • Consistent naming conventions

Testing

  • Unit tests cover new functionality
  • Edge cases are tested
  • Tests are meaningful, not just for coverage

Best Practices

  • Prioritize security issues first
  • Focus on logic errors over style nitpicks
  • Consider the reviewer's time - highlight critical items
  • Adapt checklist to project maturity level
Files

What ships with it

1 file 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. 9d ago First seen · 73 lines · 50 tokens per session scan A d2b69e965dc3

Subscribe to this mod's changes

code-review-checklist is a skill published in the GitHub repository curiositech/some_claude_skills (216 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 545 once invoked, about $0.0003 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.