review

review is a command for Claude Code from komunite/kalfa. It costs 29 tokens per session (1,017 once invoked), scanned A, original, MIT.

Deep code-review command that examines changes for security, performance, architecture, and practical fixes, not only coding style. It can review files, directories, staged changes, commits, pull requests, or branches.

In plain words
What is it for?
Use it to review a file, directory, pull request, branch, or recent changes and receive actionable findings about security, speed, design, and test coverage.
Why use it?
It helps find serious problems that a style check may miss, such as unsafe input handling, authorization gaps, hidden credentials, slow database access, or missing tests.

Command 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 commands/komunite/kalfa/review
Clone the repo
git clone --depth 1 https://github.com/komunite/kalfa

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 review

README.md
[![agentmods](https://agentmods.dev/badge/commands/komunite/kalfa/review.svg)](https://agentmods.dev/commands/komunite/kalfa/review)
Your own site
<a href="https://agentmods.dev/commands/komunite/kalfa/review"><img src="https://agentmods.dev/badge/commands/komunite/kalfa/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,017 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 $0.00029 $0.01017
Opus 5 $0.00015 $0.00508
Sonnet 5 $0.00006 $0.00203
Haiku 4.5 $0.00003 $0.00102

Measured 5d ago against content hash 4ef78b4d7cf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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 5d 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/commands/review.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kapsamlı kod incelemesi. Stilin ötesine geçer — güvenlik, performans, mimari kontrol eder ve eyleme dönüştürülebilir iyileştirme önerileri üretir.

Adımlar

Adım 1: Kapsamı belirle

Neyin inceleneceğini belirle:

  • Kullanıcı bir dosya veya dizin belirttiyse → onu incele
  • Kullanıcı bir PR veya branch belirttiyse → git diff main...HEAD (veya uygun base)
  • Hiçbir şey belirtilmediyse → aşamalı değişiklikleri (git diff --cached) veya son commit'leri incele

Adım 2: Kodu oku

Kapsamdaki tüm dosyaları oku. Büyük diff'ler için şunlara odaklan:

  • Yeni dosyalar (en yüksek risk — önceki inceleme yok)
  • En çok değişiklik yapılan dosyalar
  • Test dosyaları (veya eksiklikleri)

Adım 3: Çok boyutlu inceleme (paralel agent'lar)

Paralel inceleme agent'ları başlat:

Agent 1 — Güvenlik incelemesi:

  • Girdi doğrulama (SQL injection, XSS, komut enjeksiyonu)
  • Kimlik doğrulama / yetkilendirme boşlukları
  • Kodda gizli anahtarlar veya kimlik bilgileri
  • Güvensiz bağımlılıklar
  • OWASP İlk 10 kontrol listesi

Agent 2 — Performans incelemesi:

  • N+1 sorguları veya gereksiz veritabanı çağrıları
  • Eksik indeksler (şema görünüyorsa)
  • Sınırsız döngüler veya özyineleme
  • Büyük bellek tahsisleri
  • Eksik önbellekleme fırsatları
  • Gereksiz yeniden render'lar (React) veya yeniden hesaplamalar

Agent 3 — Mimari inceleme:

  • Bu, kod tabanındaki mevcut kalıpları takip ediyor mu?
  • Sorumluluk açıkça ayrılmış mı?
  • Döngüsel bağımlılıklar var mı?
  • Soyutlama seviyesi uygun mu? (aşırı mühendislik veya yetersiz soyutlama)
  • Test etmek, debug etmek ve bakımını yapmak kolay olacak mı?

Adım 4: Bulguları derle

Her bulguyu kategorize et:

Önem Anlam
CRITICAL Merge öncesi düzeltilmeli — güvenlik açığı, veri kaybı riski, kırıcı hata
HIGH Düzeltilmeli — performans sorunu, mimari endişe, bakım zorluğu
MEDIUM Düzeltmeyi değerlendir — kod kokusu, küçük verimsizlik, okunabilirlik iyileştirmesi
LOW Detay — stil tercihi, isimlendirme önerisi, yorum iyileştirmesi

Read the full file on GitHub · 101 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. 5d ago First seen · 101 lines · 29 tokens per session scan A 4ef78b4d7cf0

Subscribe to this mod's changes

review is a command published in the GitHub repository komunite/kalfa (244 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,017 once invoked, about $0.0001 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 2026-08-30.