adversarial-code-reviewer

adversarial-code-reviewer is a cursor rule for Cursor from GktuOktay/ai-skills. It costs 0 tokens per session (488 once invoked), scanned A, original, MIT.

A code review checker that looks for serious bugs and security gaps before code is delivered. It examines error handling, resource cleanup, simultaneous requests, and unsafe input.

In plain words
What is it for?
It is for auditing changed or refactored code for unhandled errors, memory and resource leaks, race conditions, unsafe database or HTML input, and weak type usage.
Why use it?
A normal review can miss failures that happen only in unusual cases or under load. This provides a deliberately skeptical pass focused on risks that could crash or compromise an application.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit It is for auditing changed or refactored code for unhandled errors, memory and resource leaks, race conditions, unsafe database or HTML input, and weak type usage.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/gktuoktay/ai-skills/adversarial-code-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/GktuOktay/ai-skills

Made for: Cursor.

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 adversarial-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/rules/gktuoktay/ai-skills/adversarial-code-reviewer/github.svg)](https://agentmods.dev/rules/gktuoktay/ai-skills/adversarial-code-reviewer)
Your own site
<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/adversarial-code-reviewer"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/adversarial-code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for adversarial-code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/rules/gktuoktay/ai-skills/adversarial-code-reviewer"><img src="https://agentmods.dev/badge/rules/gktuoktay/ai-skills/adversarial-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 5d ago against content hash c29261208137, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adversarial-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 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.

agents/cursor/rules/adversarial-code-reviewer.mdc · 38 lines

What it actually says

Adversarial Code Reviewer & Showstopper Inspector

Bu skill, kod yazıldıktan veya refactor edildikten hemen sonra çalışır. Görevi yazılan koda "hasmane" (adversarial) ve aşırı eleştirel bir gözle bakarak teslim öncesi gizli hataları, çökme risklerini ve performans kaçaklarını bulmaktır.


🔍 Denetim Kontrol Listesi (Showstopper Checklist)

  1. Uncaught Exceptions & Silent Crashes:

    • Unhandled promise rejection var mı?
    • Try-catch bloğunda hata yutulmuş mu?
  2. Memory Leaks & Resource Leaks:

    • Kapanmamış event listener, setInterval veya unclosed DB connection var mı?
    • React useEffect cleanup fonksiyonu eksik mi?
  3. Concurrency & Race Conditions:

    • Aynı anda birden fazla istek geldiğinde state bozulması riski var mı?
    • Async/await kullanımında race condition var mı?
  4. Security & Type Safety:

    • TypeScript any kaçamakları var mı?
    • Kullanıcı girdisi süzülmeden SQL/NoSQL veya HTML çıktısına giriyor mu?

📋 Çıktı Formatı

🧐 Hasmane Kod İncelemesi (Adversarial Audit Results)

  • 🔴 Showstopper (Kritik Risk): [Satır No / Fonksiyon] -> [Açıklama ve Çökme Riski]
  • 🟡 Gizli Mantık Hatası (Edge Case): [Açıklama]
  • 🛠️ Düzeltilmiş Güvenli Kod: [Düzeltilmiş Kod Örneği]
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 · 38 lines · 488 tokens per session scan A c29261208137

Subscribe to this mod's changes

adversarial-code-reviewer is a cursor rule published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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 2026-09-03.