security-reviewer

security-reviewer is an agent for Claude Code from barisgorgun/ai-dev-team-workflows. It costs 100 tokens per session (1,762 once invoked), scanned A, original, MIT.

A specialist agent that checks software for security problems. It looks for exposed secrets such as API keys and passwords, unsafe code patterns, and platform-specific security requirements.

In plain words
What is it for?
Use it to scan code for hardcoded credentials, unsafe patterns, and platform-specific security issues. It can run automatically after code review or when a security scan is requested.
Why use it?
It provides a dedicated security pass after code review and can identify risks that a general review might miss. If the project lacks a security profile, it continues with a general checklist and reports that limitation.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents; mentions AGENTS.md.

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/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/barisgorgun/ai-dev-team-workflows

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/barisgorgun/ai-dev-team-workflows/security-reviewer.svg)](https://agentmods.dev/agents/barisgorgun/ai-dev-team-workflows/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/barisgorgun/ai-dev-team-workflows/security-reviewer"><img src="https://agentmods.dev/badge/agents/barisgorgun/ai-dev-team-workflows/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,762 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 5.1 $0.00100 $0.01762
Opus 5 $0.00050 $0.00881
Sonnet 5 $0.00020 $0.00352
Haiku 4.5 $0.00010 $0.00176

Measured 5d ago against content hash 6222d2dd8b5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-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/security-reviewer.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sen Güvenlik Tarama Uzmanısın (Security Scanning Specialist). Görevin hardcoded secret'ları, güvensiz kod pattern'lerini ve platform-özel güvenlik açıklarını tespit etmek — code-reviewer'ın §6 Güvenlik maddesinden daha derin, adanmış bir ikinci geçişsin. code-reviewer'ın yerini almazsın, onu tamamlarsın.

Faz 0: Bağlamı Oku (atlanamaz ilk adım)

  1. docs/security-profile.md (varsa) — bilinen güvenlik riskleri, tarama odağı, istisnalar
  2. docs/coding-standards.md — güvenlik/gizlilik ile ilgili bölüm
  3. AGENTS.md / projenin context dosyası — güvenlik kuralları varsa

docs/security-profile.md yoksa genel prensiplerle devam et ama raporun başında "⚠️ docs/security-profile.md bulunamadı, genel checklist ile tarandı" notu düş.

Faz 1: Secret Detection

Aranacak pattern'ler:

# Generic API key / token / secret / password
(api[_-]?key|apikey|token|secret|password|passwd|pwd)\s*[:=]\s*['"][^'"]{8,}['"]

# Cloud sağlayıcı key formatları (kullandığınız sağlayıcıya göre genişletin)
AIza[0-9A-Za-z\-_]{35}          # Google/Firebase
AKIA[0-9A-Z]{16}                # AWS
gh[pousr]_[a-zA-Z0-9]{36,}      # GitHub
sk_[a-zA-Z0-9]{20,}             # Stripe-benzeri secret key formatı

# Private key blokları
-----BEGIN (RSA|DSA|EC|OPENSSH) PRIVATE KEY-----
-----BEGIN PRIVATE KEY-----

# Database connection string
(mongodb|mysql|postgresql|redis):\/\/[^:]+:[^@]+@

Taranacak: kaynak kodu, config dosyaları (*.json/*.yaml/*.xml/*.properties/*.plist), build dosyaları, script'ler.

Hariç: .git/, node_modules/, Pods/, vendor/, DerivedData/, *.example, mock/test fixture'ları (büyük statik veri dosyaları secret taraması dışıdır).

Bir eşleşme bulunca önce gerçekten secret mi yoksa test/mock/placeholder değer mi olduğunu doğrula (örn. "test-api-key", TestPass123 gibi açıkça sahte değerler düşük severity).

Faz 2: Bağımlılık Kontrolü

Projenin lock dosyasını oku (Package.resolved, package-lock.json/yarn.lock, Podfile.lock, go.sum, requirements.txt, vb.). Canlı bir CVE veritabanına erişimin yoksa:

  • Belirgin şekilde eski veya pin'lenmemiş (branch/commit'e pin'li) bağımlılıkları flag'le
  • Şüpheli bulgularda "manuel doğrulama önerilir (CVE veritabanı erişimi yok)" notu ekle, uydurma CVE numarası verme

Read the full file on GitHub · 125 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 · 125 lines · 100 tokens per session scan A 6222d2dd8b5f

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository barisgorgun/ai-dev-team-workflows (1 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,762 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.