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 rules/kings0527/web-reverse-engineering-skill/cursorrulesgit clone --depth 1 https://github.com/kings0527/web-reverse-engineering-skillWhat 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 | $0.01931 | $0.01931 |
| Opus 5 | $0.00966 | $0.00966 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
cursorrules 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Step 1（curl请求）：正常→L1 | 403→TLS/IP | HTML无数据→需JS How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Reverse Engineering Skill
核心原则
- Observe-first：先观察再行动，不盲目尝试
- Evidence-based：所有结论基于可验证证据
- Minimum-patch：最小化修补，够用即可
- Layer-by-layer：分层分析，从外到内逐层突破
- Verify-always：每步操作后立即验证
10分钟快速反爬判定
Step 1（curl请求）：正常→L1 | 403→TLS/IP | HTML无数据→需JS Step 2（DevTools）：challenge页→L3 | cookie特征→定性 | JS混淆→评级 Step 3（请求参数）：签名变化→L4 | 自定义Header→加密字段 Step 4（判定）：
| 结果 | 等级 | 方案 |
|---|---|---|
| curl可获取 | L1 | curl_cffi |
| 需简单cookie | L2 | 环境修补 |
| challenge页 | L3 | nodriver/patchright |
| JSVMP+签名 | L4 | VM执行追踪+操作码分析 |
| 全栈+行为 | L5 | 分层击破 |
分析路径
目标网站
├── L1-L2（无/轻度保护）→ curl_cffi + 代理池
├── L3（Challenge页）→ [自动安装WebTrace] detect_protection → hook_api → curl_cffi
├── L4 JSVMP → [强制WebTrace] analyze_jsvmp → hook_api → get_hook_logs → trace_execution
├── L4-L5 WASM → [强制WebTrace] extract_wasm → analyze_wasm → dump_wasm_memory
└── L5（组合保护）→ [强制WebTrace + nodriver] 分层击破
工具选择（强制规则）
| 场景 | 保护等级 | 必须使用 |
|---|---|---|
| TLS/HTTP2指纹 | L1-L2 | curl_cffi |
| 浏览器自动化 | L3+ | nodriver |
| JSVMP分析 | L4+ | WebTrace: analyze_jsvmp + hook_api + trace_execution |
| WASM分析 | L4+ | WebTrace: extract_wasm + analyze_wasm + dump_wasm_memory |
| 动态监控 | L3+ | WebTrace: hook_api + get_hook_logs |
| JS反混淆 | any | webcrack（离线）/ WebTrace: deobfuscate（在线） |
| 网络抓包 | any | mitmproxy / SSLKEYLOGFILE+Wireshark |
| 环境修补 | any | Node.js + Proxy监测法 |
| CDP反检测 | L3+ | nodriver / patchright / rebrowser-patches |
WebTrace 安装与连接（保护等级≥L3时强制执行）
阶段1：构建（大多数Agent可自动完成）
# 检查是否已构建
if [ ! -f "./web-trace/dist/manifest.json" ]; then
git clone --depth 1 https://github.com/kings0527/web-trace.git
cd web-trace && npm install && npm run build
fi
阶段2：加载Extension到浏览器
方式A（自动 - 推荐）：通过nodriver/patchright启动
# Python nodriver（反检测浏览器）
import nodriver as uc
browser = await uc.start(browser_args=['--load-extension=./web-trace/dist'])
方式B（自动 - CLI启动）：直接命令行启动浏览器
# Windows Edge
msedge --load-extension=./web-trace/dist --remote-debugging-port=9222
# Windows Chrome
chrome --load-extension=./web-trace/dist --remote-debugging-port=9222
# 浏览器检测（Windows）
where msedge 2>nul && set BROWSER=msedge || where chrome 2>nul && set BROWSER=chrome
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 · 174 lines · 1,931 tokens per session scan A 9fa0d5617514
cursorrules is a cursor rule published in the GitHub repository kings0527/web-reverse-engineering-skill (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,931 tokens to every session, about $0.0097 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 2026-08-31.
Other cursor rules, from other repositories
webkit-browser
Cursor rule "webkit-browser" from duckduckgo/apple-browsers, covering webkit & browser development guidelines, webview configuration, basic webview setup, user scripts management and tab management.
cypress-e2e-testing-cursorrules-prompt-file
Cursor rules for Cypress development with E2E testing.
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
node-dependencies
Enforce Node.js versioning and package management best practices.
security-standards
Cursor rule "security-standards" from wjgogogo/cursor-rules, covering 安全规范, 核心原则 [p0], 输入验证, xss 防护 and csrf 防护.