claude-skills-generator: Command for Claude Code

.claude/commands/review-code.md

review-code is a command for Claude Code from martinholovsky/claude-skills-generator. It costs 0 tokens per session (233 once invoked), scanned A, original, Unlicense.

A review command that examines recent code changes for correctness, maintainability, security, testing, and performance.

In plain words
What is it for?
Use it after making changes to view the diff, run the project's tests and linter, and receive issues, improvement suggestions, and positive findings.
Why use it?
It provides a structured second check for missed edge cases, weak error handling, duplicated or complex code, security problems, and missing tests.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is martinholovsky/claude-skills-generator's own configuration. It tells Claude Code how to work on claude-skills-generator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-skills-generator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to martinholovsky/claude-skills-generator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/martinholovsky/claude-skills-generator/main/.claude/commands/review-code.md
Clone the repo
git clone --depth 1 https://github.com/martinholovsky/claude-skills-generator

Made for: Claude Code.

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 review-code

README.md
[![agentmods](https://agentmods.dev/badge/commands/martinholovsky/claude-skills-generator/review-code.svg)](https://agentmods.dev/commands/martinholovsky/claude-skills-generator/review-code)
Your own site
<a href="https://agentmods.dev/commands/martinholovsky/claude-skills-generator/review-code"><img src="https://agentmods.dev/badge/commands/martinholovsky/claude-skills-generator/review-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 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.
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 $0.00000 $0.00233
Opus 5 $0.00000 $0.00117
Sonnet 5 $0.00000 $0.00047
Haiku 4.5 $0.00000 $0.00023

Measured 7d ago against content hash b8aa646daef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-code 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 7d 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/commands/review-code.md · 53 lines

What it actually says

Review Code

Perform a code review on recent changes.

Review Checklist

Functionality

  • Code accomplishes the intended purpose
  • Edge cases are handled
  • Error handling is appropriate

Code Quality

  • Follows project coding standards
  • No unnecessary complexity
  • Clear naming conventions
  • No code duplication

Security

  • No hardcoded secrets
  • Input validation present
  • No SQL injection vulnerabilities
  • No XSS vulnerabilities

Testing

  • Adequate test coverage
  • Tests are meaningful, not just for coverage
  • Edge cases tested

Performance

  • No obvious performance issues
  • Efficient algorithms used
  • No memory leaks

Commands

# View recent changes
git diff HEAD~1

# Run tests
{{TEST_COMMAND}}

# Run linter
{{LINT_COMMAND}}

Output

Provide feedback with:

  1. Issues found (if any)
  2. Suggestions for improvement
  3. Positive observations
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. 7d ago First seen · 53 lines · 0 tokens per session scan A b8aa646daef2

Subscribe to this mod's changes

review-code is a command published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 233 tokens. 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.