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 skills/asaiuta/reverse-workbench-skill/browser-automationnpx skills add Asaiuta/reverse-workbench-skill --skill browser-automationgit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillWrote 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/skills/asaiuta/reverse-workbench-skill/browser-automation)<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/browser-automation"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/browser-automation.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.02471 |
| Opus 5 | $0.00075 | $0.01236 |
| Sonnet 5 | $0.00030 | $0.00494 |
| Haiku 4.5 | $0.00015 | $0.00247 |
Grade A, and why
browser-automation 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.
This is a copy
92% identical to browser-automation — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自动化操作 (Desktop & Browser Automation)
ACTION REQUIRED（读完后立刻执行）
NOW：确认当前任务是否命中本 skill 的适用范围NOW：读取../tool-index.md，校验工具可用性和实际路径NEXT：缺工具时调用 bootstrap，不要猜路径ACT：进入"工作流"第一步并执行，不要停在确认状态
适用范围
当任务属于以下场景时使用本 skill：
浏览器场景（Playwright / agent-browser）
- 打开网页并操作页面元素（点击、填表、提交）
- 爬取页面内容或截图
- 自动化登录流程
- 渗透测试中与 Web 页面交互（提交 payload、触发 XSS）
- 验证码页面的自动化处理
- 批量表单提交
桌面应用场景（OpenReverse）
- 操作 Windows 桌面应用（IDA Pro、x64dbg、Wireshark 等）
- 需要视觉驱动交互（CUA 模式）
- 需要结构化 UI 操作（UIA 模式）
- 桌面应用的网络流量观察（内置 mitmproxy）
- 自动化逆向工具的 GUI 操作
- 黑盒测试桌面软件
与其他工具的分工
| 场景 | 用什么 |
|---|---|
| 操作网页（浏览器内） | Playwright / agent-browser |
| 操作桌面应用（Windows GUI） | OpenReverse |
| 抓包分析、HTTP 请求捕获 | anything-analyzer 或 OpenReverse network lane |
| JS 断点、Hook、CDP 调试 | jshookmcp |
| 定位签名算法、补环境复现 | js-reverse |
简单判断：
- 目标是网页 → Playwright
- 目标是 Windows 桌面应用 → OpenReverse
- 两者都需要 → 组合使用
Part 1: 浏览器自动化（Playwright / agent-browser）
核心工作流
# 1. 打开页面
agent-browser open <url>
# 2. 获取可交互元素（返回 @e1, @e2... 引用）
agent-browser snapshot -i
# 3. 用引用操作元素
agent-browser click @e1
agent-browser fill @e2 "text"
# 4. 完成后关闭
agent-browser close
命令参考
# 导航
agent-browser open <url>
agent-browser close
# 页面快照
agent-browser snapshot # 完整无障碍树
agent-browser snapshot -i # 仅可交互元素（推荐）
# 交互操作
agent-browser click @e1
agent-browser fill @e2 "text"
agent-browser type @e2 "text"
agent-browser press Enter
agent-browser scroll down 500
# 获取信息
agent-browser get text @e1
agent-browser get title
agent-browser get url
# 等待
agent-browser wait @e1
agent-browser wait 2000
agent-browser wait --load networkidle
注意事项
- 必须执行
agent-browser close，否则进程泄漏 - 操作前先 snapshot，不要猜元素引用
- 提交表单后用
wait --load networkidle等页面稳定
Sandbox agent-browser-cli 适配器
当当前环境提供 agent-browser-cli（受监管 Chromium 的 daemon/extension bridge）时，优先遵循 .agents/skills/agent-browser-cli/SKILL.md 的当前版本命令。它不是 Playwright，且其 profile、端口、daemon 和 extension 路径都是环境特定的；不要把 sandbox 的 /data、/opt/agent-browser 或 supervisord 假设带入 Windows 主机。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 257 lines · 149 tokens per session scan A 543858dc7197
browser-automation is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 21d ago), licensed MIT. It adds 149 tokens to every session and 2,471 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to browser-automation, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
xs-leaks
XS-Leaks — cross-site information leaks via timing, frame counting, navigation, error oracles. Side-channel attacks against same-origin authenticated state.
ctf-web
CTF Web攻击知识库 — PHP弱比较绕过、命令注入空格绕过、eval回显技巧、SSTI注入链、反序列化利用链、PHP代码审计checklist、常见flag位置.
osint-recon
OSINT 开源情报收集知识库 — 四维信息收集模型（服务器→网站→域名→人员），维度四（人员信息）条件触发.
crypto-toolkit
编码解码与加解密工具 — base64/URL/Hex/HTML实体编码解码，MD5/SHA哈希，AES/DES/RSA加解密，JWT解析，Caesar/ROT13密码，栅栏/Vigenere密码，Unicode转义，Morse电码等.
hackerone
HackerOne 赏金项目 scope-guard 流程 — 读取 program scope，强制 scope 与 program rules，再逐个把 in-scope asset 交给 pentest-flow.
redteam-cve-lookup
CVE lookup and applicability assessment domain card. Use after reconnaissance has identified products, versions, services, or fingerprints and red-team mode needs evidence-based CVE matching before deeper testing.