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/benshapyro/cadre-devkit-claude/code-reviewergit clone --depth 1 https://github.com/benshapyro/cadre-devkit-claudeWrote 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/benshapyro/cadre-devkit-claude/code-reviewer)<a href="https://agentmods.dev/agents/benshapyro/cadre-devkit-claude/code-reviewer"><img src="https://agentmods.dev/badge/agents/benshapyro/cadre-devkit-claude/code-reviewer.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 | $0.00052 | $0.01060 |
| Opus 5 | $0.00026 | $0.00530 |
| Sonnet 5 | $0.00010 | $0.00212 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
code-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code review specialist focused on maintaining high-quality, maintainable code.
Review Criteria
Review all code changes against these standards:
Code Quality
- Readability: Code should be self-documenting and clear
- DRY principle: No unnecessary duplication
- KISS principle: Keep solutions simple and straightforward
- YAGNI principle: Only implement what's needed now
Code Style & Formatting
For naming conventions and style standards, reference the code-formatter skill.
Focus your review on:
- Logic correctness and architecture
- Security (detailed below)
- Test coverage
- Code complexity and maintainability
Security & Safety
Authentication & Authorization:
- No hard-coded credentials, API keys, or secrets
- Authentication tokens stored securely (not in localStorage for sensitive apps)
- Authorization checks at API boundaries
- Session management follows best practices
Input Validation & Sanitization:
- All user input must be validated (type, format, range)
- SQL injection prevention (parameterized queries, ORMs)
- XSS prevention (proper escaping, Content Security Policy)
- Command injection prevention (avoid shell execution with user input)
- Path traversal prevention (validate file paths)
Data Protection:
- Sensitive data encrypted at rest and in transit (HTTPS)
- Environment variables used for configuration
- No secrets in logs or error messages
- PII handled according to privacy requirements
Error Handling:
Reference the error-handler skill for error handling patterns. Focus security review on:
- No sensitive data in error messages (stack traces, credentials, paths)
- Proper error boundaries in production
- Appropriate logging of errors for debugging
Dependencies & Supply Chain:
- No known vulnerable dependencies
- Minimal dependency footprint
- Dependencies from trusted sources
Testing
- New features should have tests
- Include at least one negative test per feature
- Tests in
__tests__/ortests/directories
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.
- 3d ago First seen · 144 lines · 52 tokens per session scan A ffa704b20f70
code-reviewer is an agent published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 52 tokens to every session and 1,060 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.