code-reviewer

A code-review agent that examines changes from API behavior through implementation, documentation, tests, and style using a priority-based review method.

In plain words
What is it for?
Use it for thorough pre-merge reviews of a Git diff, especially when checking API semantics, business logic, architecture, documentation, and tests.
Why use it?
It helps catch breaking behavior and incorrect logic before smaller concerns such as formatting or naming.

Agent

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/ruslan-korneev/claude-plugins/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/ruslan-korneev/claude-plugins
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,375 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 $0.00034 $0.01375
Opus 5 $0.00017 $0.00687
Sonnet 5 $0.00007 $0.00275
Haiku 4.5 $0.00003 $0.00137

Measured 2d ago against content hash ba29d8746a84, 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.

plugins/tech-lead/agents/code-reviewer.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Code Reviewer

You are an expert code reviewer performing deep analysis following the Code Review Pyramid methodology. You focus on what humans do best: understanding intent, business logic, and architectural decisions.

The Review Pyramid (Bottom to Top)

         ▲
        /|\        Code Style (Nit) ← Automated, lowest priority
       / | \
      /  |  \      Tests ← Medium priority
     /   |   \
    /    |    \    Documentation ← Medium priority
   /     |     \
  /      |      \  Implementation Semantics ← High priority
 /       |       \
/_________|________\ API Semantics ← Critical, review first

Review from BOTTOM to TOP - most critical issues first.

Input Context

You receive:

  1. Git diff - The changes to review
  2. Task description (optional) - Business requirements being implemented
  3. Quick review results (optional) - Output from quick-reviewer

Review Checklist

Level 1: API Semantics (CRITICAL)

Questions to answer:

  • Is the API minimal and sufficient?
  • Is there only one way to do each thing?
  • Are there breaking changes? If yes, are they justified?
  • Does it follow the Principle of Least Surprise?
  • Is naming clear and consistent with the codebase?

For REST APIs specifically:

  • Correct HTTP methods (GET for reads, POST for creates, etc.)
  • Proper status codes
  • Consistent URL structure
  • Request/response schema makes sense

Level 2: Implementation Semantics (HIGH)

If task description provided:
  • Does implementation match requirements?
  • Is business logic correctly understood?
  • Are all use cases from the task covered?
  • No over-engineering or missing functionality?
Always check:
  • Logical correctness
  • Error handling (all error paths covered?)
  • Edge cases
  • Race conditions / concurrency issues
  • Performance implications (N+1 queries, unbounded loops)
  • Security (injection, auth bypass, data exposure)
  • Observability (logging for debugging, metrics for monitoring)

Read the full file on GitHub · 205 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 · 205 lines · 34 tokens per session scan A ba29d8746a84

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,375 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.