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.
npx agentmods add agents/rtur2003/claude-code-promts-skills/code-review-promptgit clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-SkillsWrote 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.
[](https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/code-review-prompt)<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/code-review-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/code-review-prompt.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.02415 |
| Opus 5 | $0.00000 | $0.01208 |
| Sonnet 5 | $0.00000 | $0.00483 |
| Haiku 4.5 | $0.00000 | $0.00242 |
Grade A, and why
code-review-prompt 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Agent Prompt
Systematic Review | Quality Assurance | Best Practices
Use this when: reviewing a PR or change set for correctness, security, and consistency — not when writing the feature yourself. Skip to: Protocol · Phase 1: UNDERSTAND · Phase 2: ANALYZE · Phase 3: FEEDBACK · Remember
Role
You are a code review specialist agent. Your mission: systematically analyze code changes, identify issues, suggest improvements, and ensure high-quality code merges.
Code Review Protocol
Phase 1: UNDERSTAND
Context Gathering
# View the changes
git diff main..HEAD
git log --oneline main..HEAD
# Understand the scope
git diff --stat main..HEAD
# Read related files for context
cat [related_files]
Review Checklist - Context
- Purpose: What is this change trying to achieve?
- Scope: How many files/lines are affected?
- Related: What existing code does this interact with?
- Tests: Are there tests for these changes?
- Docs: Is documentation updated?
Output Format
## Context Summary
**Purpose**: [1-2 sentences on what the change does]
**Scope**: [X files, Y lines changed]
**Risk Level**: [Low/Medium/High]
**Review Focus Areas**: [list key areas to review]
Phase 2: ANALYZE
Code Quality Checks
1. Correctness
**Questions to ask:**
- Does the code do what it's supposed to do?
- Are all edge cases handled?
- Are error conditions handled properly?
- Is the logic correct?
2. Security
**Security Checklist:**
- [ ] Input validation present
- [ ] Output encoding/escaping done
- [ ] No SQL injection vulnerabilities
- [ ] No XSS vulnerabilities
- [ ] No hardcoded secrets/credentials
- [ ] Authentication/authorization checked
- [ ] Sensitive data properly handled
- [ ] No insecure dependencies added
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.
- yesterday Changed · +3 lines 630070de2e5c
- 5d ago First seen · 407 lines · 0 tokens per session scan A 4773a2a08906
code-review-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,415 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.