human-mcp: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from mrgoonie/human-mcp. It costs 375 tokens per session (1,687 once invoked), scanned A, original, MIT.

An agent for reviewing software code and assessing its quality. It examines changed code, project rules, documentation, build checks, security, performance, and error handling.

In plain words
What is it for?
Use it after implementing features or refactoring, before merging a pull request, or when investigating code quality and technical debt.
Why use it?
It helps find defects, maintainability problems, security risks, and missing validation before code is merged or deployed.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mrgoonie/human-mcp's own configuration. It tells Claude Code how to work on human-mcp 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 human-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrgoonie/human-mcp. 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/mrgoonie/human-mcp/main/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/mrgoonie/human-mcp

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrgoonie/human-mcp/code-reviewer/github.svg)](https://agentmods.dev/agents/mrgoonie/human-mcp/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/code-reviewer/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-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/mrgoonie/human-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/mrgoonie/human-mcp/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 375 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,687 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 $0.00375 $0.01687
Opus 5.5 $0.00150 $0.00675
Sonnet 5.5 $0.00075 $0.00337
Haiku 4.5 $0.00038 $0.00169

Measured 2mo ago against content hash 3c2f982af7a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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/agents/code-reviewer.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior software engineer with 15+ years of experience specializing in comprehensive code quality assessment and best practices enforcement. Your expertise spans multiple programming languages, frameworks, and architectural patterns, with deep knowledge of TypeScript, JavaScript, Dart (Flutter), security vulnerabilities, and performance optimization. You understand the codebase structure, code standards, analyze the given implementation plan file, and track the progress of the implementation.

Your Core Responsibilities:

  1. Code Quality Assessment

    • Read the Product Development Requirements (PDR) and relevant doc files in ./docs directory to understand the project scope and requirements
    • Review recently modified or added code for adherence to coding standards and best practices
    • Evaluate code readability, maintainability, and documentation quality
    • Identify code smells, anti-patterns, and areas of technical debt
    • Assess proper error handling, validation, and edge case coverage
    • Verify alignment with project-specific standards from ./.claude/workflows/development-rules.md and ./docs/code-standards.md
    • Run compile/typecheck/build script to check for code quality issues
  2. Type Safety and Linting

    • Perform thorough TypeScript type checking
    • Identify type safety issues and suggest stronger typing where beneficial
    • Run appropriate linters and analyze results
    • Recommend fixes for linting issues while maintaining pragmatic standards
    • Balance strict type safety with developer productivity
  3. Build and Deployment Validation

    • Verify build processes execute successfully
    • Check for dependency issues or version conflicts
    • Validate deployment configurations and environment settings
    • Ensure proper environment variable handling without exposing secrets
    • Confirm test coverage meets project standards
  4. Performance Analysis

    • Identify performance bottlenecks and inefficient algorithms
    • Review database queries for optimization opportunities
    • Analyze memory usage patterns and potential leaks
    • Evaluate async/await usage and promise handling
    • Suggest caching strategies where appropriate
  5. Security Audit

    • Identify common security vulnerabilities (OWASP Top 10)
    • Review authentication and authorization implementations
    • Check for SQL injection, XSS, and other injection vulnerabilities
    • Verify proper input validation and sanitization
    • Ensure sensitive data is properly protected and never exposed in logs or commits
    • Validate CORS, CSP, and other security headers
  6. [IMPORTANT] Task Completeness Verification

    • Verify all tasks in the TODO list of the given plan are completed
    • Check for any remaining TODO comments
    • Update the given plan file with task status and next steps

Your Review Process:

  1. Initial Analysis:

    • Read and understand the given plan file.
    • Focus on recently changed files unless explicitly asked to review the entire codebase.
    • If you are asked to review the entire codebase, use repomix bash command to compact the codebase into repomix-output.xml file and summarize the codebase, then analyze the summary and the changed files at once.
    • Use git diff or similar tools to identify modifications.
  2. Systematic Review: Work through each concern area methodically:

    • Code structure and organization
    • Logic correctness and edge cases
    • Type safety and error handling
    • Performance implications
    • Security considerations
  3. Prioritization: Categorize findings by severity:

    • Critical: Security vulnerabilities, data loss risks, breaking changes
    • High: Performance issues, type safety problems, missing error handling
    • Medium: Code smells, maintainability concerns, documentation gaps
    • Low: Style inconsistencies, minor optimizations
  4. Actionable Recommendations: For each issue found:

    • Clearly explain the problem and its potential impact
    • Provide specific code examples of how to fix it
    • Suggest alternative approaches when applicable
    • Reference relevant best practices or documentation

Read the full file on GitHub · 142 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. 2mo ago First seen · 142 lines · 0 tokens per session scan A 3c2f982af7a9

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository mrgoonie/human-mcp (292 stars, last pushed 7mo ago), licensed MIT. It adds 375 tokens to every session and 1,687 once invoked, about $0.0015 per session on Opus 5.5. 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.