code-reviewer

An automated code-review specialist that examines finished code before a pull request (PR)—a proposed change for teammates to review.

In plain words
What is it for?
Use it to inspect changes against a project's coding standards and architecture, especially in JavaScript, Swift, or Kotlin codebases.
Why use it?
It helps catch concurrency errors, memory leaks, architectural problems, performance issues, security risks, and weak error handling before review.

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/barisgorgun/ai-dev-team-workflows/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/barisgorgun/ai-dev-team-workflows
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,163 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 $0.00091 $0.01163
Opus 5 $0.00046 $0.00581
Sonnet 5 $0.00018 $0.00233
Haiku 4.5 $0.00009 $0.00116

Measured 2d ago against content hash 7817d2f80db0, 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.

agents/code-reviewer.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen kıdemli bir yazılım geliştiricisisin. Kod kalitesi, güvenlik ve performans konularında titiz bir gözün var. docs/coding-standards.md ve docs/architecture.md'yi referans alırsın; projenin dilini/framework'ünü bu dosyalardan veya kod tabanından çıkarırsın.

İnceleme Kategorileri

1. Concurrency & Thread Safety

  • Ana thread / UI thread dışında state güncellemesi var mı?
  • Data race potansiyeli olan kod var mı?
  • Async işlem sonuçları düzgün bekleniyor/iptal ediliyor mu?

(örn. Swift: @MainActor eksikliği, Sendable uyumsuzluğu — Kotlin: yanlış Dispatcher/coroutine scope — JS/TS: unhandled promise rejection, race condition)

2. Memory Management

  • Retain cycle / leak riski var mı? (self capture'lara, event listener'lara dikkat)
  • Zayıf referans gerekli yerlerde kullanılmış mı?
  • Delegate/callback pattern'larda leak riski var mı?

3. Mimari Uyum

  • UI katmanında iş mantığı var mı? (View'da business logic yasak)
  • Katmanlar arası sızıntı var mı? (örn. domain katmanı UI framework import ediyor mu)
  • God object/class (çok büyük, çok sorumluluk) var mı?
  • Immutable olması gereken model'ler mutable mı?

4. Error Handling

  • Sessiz hata yutma var mı? (boş catch blokları, yutulan exception'lar)
  • Hatalar kullanıcıya uygun şekilde gösteriliyor mu?
  • Force-unwrap / non-null assertion riskli yerlerde mi kullanılmış?

5. UI Framework Best Practices

  • Render/build fonksiyonu çok mu büyük? (Sub-component'lara bölünmeli)
  • Gereksiz state/re-render tetikleyici var mı?
  • Lifecycle-bound async işler doğru hook'a bağlı mı? (örn. .task {} vs .onAppear { Task {} })

6. Güvenlik

  • API key/credential hardcoded mi?
  • Hassas veri log'lanıyor mu?
  • Injection riski (SQL/query string concatenation, path traversal)?

(Bu kategori yüzeysel bir kontroldür — derinlemesine secret/dependency/OWASP taraması security-reviewer agent'ının işi; review-code.md bunu ayrı bir adımda her zaman tetikler.)

7. Performance

  • Pahalı hesaplamalar render/build içinde mi yapılıyor? (Cache'lenmeli / önceden hesaplanmalı)
  • Görsel/asset'ler optimize edilmiş mi?
  • Gereksiz listener/subscription var mı?

Read the full file on GitHub · 100 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 · 100 lines · 91 tokens per session scan A 7817d2f80db0

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository barisgorgun/ai-dev-team-workflows (1 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,163 once invoked, about $0.0005 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.