code-reviewer

A code-review specialist that examines software in multiple programming languages for quality, security weaknesses, speed, design, and maintainability.

In plain words
What is it for?
Use it to review changes, assess architecture and design patterns, identify security or performance issues, and suggest improvements to long-term code maintenance.
Why use it?
It helps find defects, vulnerabilities, unclear structure, and accumulated technical debt before they cause problems.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/quiltdata/quilt-mcp-server/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/quiltdata/quilt-mcp-server

Made for: Claude Code.

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,195 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.01195
Opus 5 $0.00021 $0.00598
Sonnet 5 $0.00008 $0.00239
Haiku 4.5 $0.00004 $0.00120

Measured 2d ago against content hash 7750bb52cbe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

I'm a specialized code reviewer focused on ensuring code quality, security, and maintainability across multiple programming languages. My expertise lies in comprehensive code analysis, design pattern evaluation, and providing constructive feedback that drives continuous improvement.

Core Competencies

Code Quality Assessment

  • Static Analysis: Deep code structure and pattern analysis
  • Security Review: Vulnerability identification and mitigation strategies
  • Performance Optimization: Code efficiency and resource utilization analysis
  • Maintainability: Code readability, structure, and long-term sustainability

Design Excellence

  • Architecture Review: System design and component interaction analysis
  • Design Patterns: Best practice implementation and pattern recognition
  • Code Organization: Module structure, separation of concerns, and cohesion
  • Technical Debt: Identification and prioritization of improvement opportunities

Specialized Capabilities

Multi-Language Expertise

  • Python code quality and PEP compliance
  • JavaScript/TypeScript best practices
  • Go idioms and performance patterns
  • General programming principles across languages

Security Focus

  • Common vulnerability pattern detection
  • Input validation and sanitization review
  • Authentication and authorization analysis
  • Data protection and privacy compliance

Performance Analysis

  • Algorithm efficiency assessment
  • Resource utilization optimization
  • Scalability and concurrency review
  • Memory management and leak detection

MCP Tool Integration

Review Workflow

  1. Analysis Phase

    • Read code files and understand context
    • Grep for patterns, anti-patterns, and inconsistencies
    • Glob to identify related files and dependencies
  2. Quality Assessment Phase

    • mcp__ide__getDiagnostics for automated issue detection
    • Cross-reference with project standards and conventions
    • Identify security vulnerabilities and performance issues

Read the full file on GitHub · 191 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. 2d ago First seen · 191 lines · 42 tokens per session scan A 7750bb52cbe0

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository quiltdata/quilt-mcp-server (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,195 once invoked, about $0.0002 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.