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 skills add seaworld008/Commonly-used-high-value-skills --skill agent-browsergit clone --depth 1 https://github.com/seaworld008/Commonly-used-high-value-skillsWrote 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/seaworld008/commonly-used-high-value-skills/agent-browser)<a href="https://agentmods.dev/skills/seaworld008/commonly-used-high-value-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/seaworld008/commonly-used-high-value-skills/agent-browser/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/skills/seaworld008/commonly-used-high-value-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/seaworld008/commonly-used-high-value-skills/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00037 | $0.01934 |
| Opus 5 | $0.00018 | $0.00967 |
| Sonnet 5 | $0.00007 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
agent-browser 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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser
当任务需要 直接操作网页(而不是只读 API 数据)时使用本技能。Agent Browser 基于标准的 CDP (Chrome DevTools Protocol) 协议,赋予 Agent 像人类一样浏览网页、填写表单、点击按钮以及处理复杂前端交互(如 React/Vue 渲染页面、弹窗、验证码预览)的能力。
安装
npx clawhub@latest install agent-browser
适用场景
- 打开网页并执行多步操作:登录后台管理系统、在多个页签间比对数据、提交复杂的业务表单。
- 用自然语言定位元素:无需编写复杂的 CSS Selector,直接通过“点击左上角的搜索框”或“找到包含‘加入购物车’字样的按钮”进行操作。
- 导出多媒体产出:将当前页面保存为高清截图、滚动截长图、PDF 文档,甚至录制一段操作视频。
- 执行页面内 JavaScript:直接在 Console 中注入自定义脚本,提取原本难以抓取的动态数据或模拟特定用户行为。
- 保存会话状态:支持 Cookie、LocalStorage 的持久化(
retain机制),实现跨会话的免登录访问。
使用建议
- 先说明目标页面与预期结果:建立清晰的
Success Criteria。 - 分阶段执行:将复杂操作拆成可验证的原子步骤(导航 → 定位 → 操作 → 校验)。
- 涉及账号安全:优先使用隔离的浏览器 Profile,并开启最小权限模式。
- 视觉优先:在关键操作前后进行
screenshot,既是留存证据,也方便 Agent 自我纠错。
触发条件 / When to Use
- API 缺失场景:当目标网站不提供公开 API,只能通过网页前端交互获取数据时。
- 图形化报表抓取:需要从复杂的仪表盘(Dashboard)中截取特定图表并分析。
- 自动化注册/登录流程:需要模拟用户完成一系列实人认证或偏好设置步骤。
- SEO 与前端性能测试:通过
console读取页面报错、性能指标(LCP, FID)并进行诊断。 - 动态内容实时监控:如监控股市实时行情网页或秒杀活动的库存变动。
核心能力 / Core Capabilities
1. 语义化快照与定位 (Semantic Snapshot)
- 操作步骤:
- 调用
snapshot获取辅助功能树(Accessibility Tree)。 - 结合
ax*(可访问性引用)和n*(DOM 引用)理解页面层级。 - 通过
highlight技能验证定位是否准确。
- 调用
- 最佳实践:在复杂页面中,先进行
scroll滚动到底部,确保懒加载(Lazy Loading)的内容完整呈现。
2. 精准动作模拟 (Action Emulation)
- 操作步骤:
- 调用
act接口,执行click,type,hover,drag等动作。 - 设置
clearFirst: true确保输入框内容干净。 - 对于关键步骤,开启
slowly: true以模仿人类真实点击频率,降低被反爬引擎识别的风险。
- 调用
- 最佳实践:在点击“提交”后,立即配合
wait工具,直到特定 URL 或文字出现,确保操作已生效。
3. 会话留存与持久化 (Session Retention)
- 操作步骤:
- 使用
retain: true标记重要的页签(Tab)。 - 被标记的页签在 Agent 会话结束后不会被自动关闭,方便后续二次访问。
- 使用
- 最佳实践:在需要用户手动扫码登录时,开启
retain,等用户扫码完成后 Agent 再接管。
4. 异常捕获与诊断 (Errors & Requests)
- 操作步骤:
- 实时读取
errors列表,识别 JS 执行崩溃。 - 监控
requests网络请求,拦截并分析特定的 API 数据包(甚至包括 XHR/Fetch 的 Response)。
- 实时读取
常用命令/模板 / Common Patterns
网页信息采集工作流模板 (Scraping Workflow)
### 任务目标
[目标描述:从 X 网站抓取前 10 个产品的价格和评论]
### 操作步骤 (Action Sequence)
1. **Navigate**: 访问 `https://example.com/products`。
2. **Wait**: 等待包含 `.product-list` 的元素加载完成。
3. **Scroll**: 滚动至页面底部触发分页。
4. **Snapshot**: 获取所有 `n` 级引用的文本内容。
5. **Console**: 注入脚本 `Array.from(document.querySelectorAll('.price')).map(e => e.innerText)`。
6. **Screenshot**: 截取整个列表区域存入 `output/products.png`。
### 预期结果
- 汇总 JSON 数据。
- 截图证据。
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.
- 11d ago First seen · 138 lines · 37 tokens per session scan A 481d9840cd78
agent-browser is a skill published in the GitHub repository seaworld008/Commonly-used-high-value-skills (70 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 1,934 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
omh-browser
This is a Hermes-native browser-operator workflow skill.