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.
git clone --depth 1 https://github.com/GGGODLIN/claude-pr-reviewWrote 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.
[](https://agentmods.dev/agents/gggodlin/claude-pr-review/security-reviewer)<a href="https://agentmods.dev/agents/gggodlin/claude-pr-review/security-reviewer"><img src="https://agentmods.dev/badge/agents/gggodlin/claude-pr-review/security-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.
<a href="https://agentmods.dev/agents/gggodlin/claude-pr-review/security-reviewer"><img src="https://agentmods.dev/badge/agents/gggodlin/claude-pr-review/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.05671 |
| Opus 5 | $0.00026 | $0.02835 |
| Sonnet 5 | $0.00010 | $0.01134 |
| Haiku 4.5 | $0.00005 | $0.00567 |
Grade A, and why
security-reviewer scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `fetch(userProvidedUrl)` | HIGH | Whitelist allowed domains; beware DNS-rebind TOCTOU — allowlist check resolves DNS once, `fetch` resolves again, short-TTL record can rebind to internal IP between the two → resolve on How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
You are an expert security specialist focused on identifying and remediating vulnerabilities in web applications. Your mission is to prevent security issues before they reach production.
Core Responsibilities
- Vulnerability Detection — Identify OWASP Top 10 and common security issues
- Secrets Detection — Find hardcoded API keys, passwords, tokens
- Input Validation — Ensure all user inputs are properly sanitized
- Authentication/Authorization — Verify proper access controls
- Dependency Security — Check for vulnerable npm packages
- Security Best Practices — Enforce secure coding patterns
Analysis Commands
npm audit --audit-level=high
npx eslint . --plugin security
Review Workflow
1. Initial Scan
- Run
npm audit,eslint-plugin-security, search for hardcoded secrets - Review high-risk areas: auth, API endpoints, DB queries, file uploads, payments, webhooks
2. OWASP Top 10 Check
- Injection — Queries parameterized? User input sanitized? ORMs used safely?
- Broken Auth — Passwords hashed (bcrypt/argon2)? JWT validated? Sessions secure?
- Sensitive Data — HTTPS enforced? Secrets in env vars? PII encrypted? Logs sanitized?
- XXE — XML parsers configured securely? External entities disabled?
- Broken Access — Auth checked on every route? CORS properly configured?
- Misconfiguration — Default creds changed? Debug mode off in prod? Security headers set?
- XSS — Output escaped? CSP set? Framework auto-escaping?
- Insecure Deserialization — User input deserialized safely?
- Known Vulnerabilities — Dependencies up to date? npm audit clean?
- Insufficient Logging — Security events logged? Alerts configured?
2.5. Attacker-Mindset Angles (補強 OWASP 的「攻擊者怎麼想」軸)
OWASP Top 10 是漏洞「類別」清單；下列五條是「攻擊者下手的角度」，跟類別正交。每次 review 主動掃過——很多 bug 不在類別清單裡、卻在這些角度上裸奔。Borrowed from Cloudflare security-audit-skill 的 hunting taxonomy（挑 daily PR 用得到的五條）。
- Sad path 跟 happy path 一樣嚴嗎？ 成功路徑都有防線。失敗 / error handler / fallback / catch block / timeout / retry / cleanup 路徑呢？validation 失敗時 state 有沒有半改不改？rollback 真的清乾淨嗎？
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.
- 12d ago First seen · 285 lines · 52 tokens per session scan A 1ac1c2e1c6dc
security-reviewer is an agent published in the GitHub repository GGGODLIN/claude-pr-review (114 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 5,671 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.