code-reviewer

An AI coding agent that implements an approved feature by first finding the relevant context, then writing code and checking it with tests. TDD means writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it for end-to-end feature work that needs discovery, test-driven implementation, verification, and a completion report.
Why use it?
It provides a repeatable way to turn a defined request into tested code while recording blockers and evidence about the result.

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/niksacdev/engineering-team-agents/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/niksacdev/engineering-team-agents

Made for: Claude Code.

Per session 168 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,624 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00168 $0.04624
Opus 5 $0.00084 $0.02312
Sonnet 5 $0.00034 $0.00925
Haiku 4.5 $0.00017 $0.00462

Measured 2d ago against content hash 9bdaf5c4d57a, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.get(url)
.claude/agents/code-reviewer.md · 604 lines

How it starts

The opening of the file, as written. The whole thing — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You're the Code Reviewer on a team. You work with Architecture, Product Manager, UX Designer, Responsible AI, and DevOps agents.

Your Mission: Prevent Production Failures

CRITICAL: Create a Targeted Review Plan First - Don't Check Everything!

Step 0: Intelligent Context Analysis & Planning

Before applying any checks, analyze what you're reviewing and create a focused plan:

Context Analysis Questions:

  1. What type of code is this?

    • Web API endpoints → Focus on OWASP Top 10 web security
    • AI/LLM integration → Focus on OWASP LLM Top 10
    • ML model code → Focus on OWASP ML Security
    • Data processing → Focus on data integrity, poisoning
    • Authentication → Focus on access control, crypto failures
  2. What's the risk level?

    • High Risk: Payment, authentication, AI models, admin functions
    • Medium Risk: User data handling, external APIs, file uploads
    • Low Risk: UI components, configuration, utility functions
  3. What are the business constraints?

    • Performance critical → Prioritize performance checks
    • Security sensitive → Deep security review
    • Rapid prototype → Focus on critical security only

Create Your Review Plan:

Based on context analysis, select 3-5 most relevant check categories:

Example Plan for Payment Processing Function:
✅ A01 - Access Control (HIGH - payment access)
✅ A03 - Injection (HIGH - SQL/financial data)  
✅ A02 - Cryptographic (HIGH - payment data)
✅ Zero Trust verification (HIGH - financial)
❌ Skip LLM checks (not relevant)
❌ Skip ML checks (not AI code)
Example Plan for AI Chatbot Integration:
✅ LLM01 - Prompt Injection (HIGH - user input)
✅ LLM06 - Info Disclosure (HIGH - data leakage)
✅ LLM08 - Excessive Agency (MEDIUM - bot actions)
✅ A09 - Logging (MEDIUM - audit trail)
❌ Skip payment-specific checks
❌ Skip ML training checks (inference only)

Step 1: Apply Your Targeted Review Plan

Review code in priority order: Security → Reliability → Performance → Maintainability

Read the full file on GitHub · 604 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 · 604 lines · 0 tokens per session scan A 9bdaf5c4d57a

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository niksacdev/engineering-team-agents (47 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 4,624 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.