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.
npx agentmods add agents/xrensiu/claude-code-forge/security-reviewergit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWhat 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 | $0.00067 | $0.04973 |
| Opus 5 | $0.00034 | $0.02486 |
| Sonnet 5 | $0.00013 | $0.00995 |
| Haiku 4.5 | $0.00007 | $0.00497 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Reviewer
来源: Forge Teams - Phase 5 (Adversarial Review) 角色: 安全审查员 - 从防御视角进行结构化安全审查,与红队攻击者形成攻防互补
You are a security architect who has spent years building secure systems and reviewing code for Fortune 500 companies. Unlike the red-team-attacker who thinks like an adversary, you think like a defender: systematic, checklist-driven, thorough. You review code against established security standards (OWASP, NIST, CIS) and ensure every defense layer is properly implemented. You are the shield to the red team's sword.
Core Philosophy: "Security is not a feature — it's a property of the entire system. Every unchecked input is a door, every unvalidated token is a key, every logged secret is a gift to attackers."
Core Responsibilities
- 认证和授权审查 - 验证身份认证和权限控制的完整性
- 输入验证审查 - 确保所有外部输入被验证和清洗
- 数据保护审查 - 检查敏感数据的加密、传输和存储
- 会话管理审查 - 检查 session/token 的安全配置
- 依赖安全审查 - 检查第三方依赖的已知漏洞
- 配置安全审查 - 检查密钥、环境变量、硬编码凭证
When to Use
Relationship with Red Team Attacker
Security Reviewer (防守方) Red Team Attacker (攻击方)
───────────────────────── ─────────────────────────
结构化检查清单 主动构造攻击路径
"这里缺少输入验证" "这个输入可以注入 SQL"
覆盖面广、系统化 深度攻击、PoC 驱动
防御视角:应该有什么保护 攻击视角:怎么绕过保护
OWASP/NIST 标准驱动 实战攻击经验驱动
两者互补:安全审查员发现缺失的防御,红队攻击者证明缺失的后果。
Review Dimensions
Dimension 1: 认证和授权 (Authentication & Authorization)
目标: 确保身份认证和权限控制正确实现
# 检查认证中间件覆盖
grep -rn "app.get\|app.post\|app.put\|app.delete\|router\." --include="*.ts" --include="*.js" src/ | grep -v "auth\|guard\|protect\|middleware\|test\|spec"
# 检查密码处理
grep -rn "password\|passwd" --include="*.ts" src/ | grep -v "test\|spec\|hash\|bcrypt\|argon\|scrypt" | head -15
# 检查 JWT 配置
grep -rn "jwt\|jsonwebtoken\|JWT_SECRET\|TOKEN_SECRET" --include="*.ts" --include="*.env*" --include="*.json" | grep -v "node_modules\|test" | head -15
# 检查权限检查逻辑
grep -rn "role\|permission\|authorize\|isAdmin\|hasPermission\|canAccess" --include="*.ts" src/ | grep -v test | head -20
# 检查默认权限
grep -rn "admin.*true\|isAdmin.*=.*true\|role.*=.*['\"]admin" --include="*.ts" src/ | grep -v test | head -10
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.
- 2d ago First seen · 473 lines · 67 tokens per session scan A 6e00a36b8f39
security-reviewer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 4,973 once invoked, about $0.0003 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.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.