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 xyva-yuangui/XyvaClaw --skill browser-pilotgit clone --depth 1 https://github.com/xyva-yuangui/XyvaClawWrote 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/xyva-yuangui/xyvaclaw/browser-pilot)<a href="https://agentmods.dev/skills/xyva-yuangui/xyvaclaw/browser-pilot"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/browser-pilot/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/xyva-yuangui/xyvaclaw/browser-pilot"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/browser-pilot.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 | $0.00054 | $0.00970 |
| Opus 5 | $0.00027 | $0.00485 |
| Sonnet 5 | $0.00011 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
browser-pilot 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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 browser-pilot（增强版）
✅ 状态：增强版已上线，功能完整。
功能
基础操作
- 导航 (navigate) - 访问 URL
- 截图 (screenshot) - 页面截图（支持整页）
- 点击 (click) - 点击元素
- 填写 (fill) - 填写表单
- 提取文本 (extract_text) - 提取页面/元素文本
- 提取 HTML (extract_html) - 提取页面/元素 HTML
- 等待 (wait) - 等待指定时间
增强功能（新增）
- 文件上传 (upload_file) - 上传文件到表单
- 文件下载 (download_file) - 下载文件
- 多标签页 (switch_tab/new_tab/close_tab) - 标签页管理
浏览器支持
- Chromium（Chrome）
- Firefox
- WebKit（Safari）
反检测
- 隐藏 webdriver 特征
- 隐藏 automation 特征
- 随机 User-Agent
- 模拟人类操作延迟
使用方法
通过技能调用
用户说"打开网页"、"截图"、"自动化操作"时自动触发。
直接脚本调用
# 健康检查
python3 scripts/browse.py --check
# 访问网页
python3 scripts/browse.py --url "https://example.com"
# 访问网页并截图
python3 scripts/browse.py --url "https://example.com" --screenshot
# 访问网页并提取文本
python3 scripts/browse.py --url "https://example.com" --extract "h1"
# 有头模式（显示浏览器窗口）
python3 scripts/browse.py --url "https://example.com" --headed
# 自定义延迟
python3 scripts/browse.py --url "https://example.com" --slow-mo 500
Python API 调用
from browse import BrowserPilot
with BrowserPilot(headless=True, slow_mo=100) as pilot:
# 启动
pilot.start("chromium")
# 导航
pilot.navigate("https://example.com")
# 截图
pilot.screenshot("output.png")
# 点击
pilot.click("#login-button")
# 填写表单
pilot.fill("#username", "myuser")
pilot.fill("#password", "mypass")
# 提取文本
text = pilot.extract_text("h1")
print(text["text"])
# 关闭（with 语句自动关闭）
技术实现
基于 playwright Python 库实现，提供同步 API。
安装
# 安装 playwright
pip install playwright
# 安装浏览器
playwright install
限制
- 复杂验证码（CAPTCHA）无法自动破解，需人工干预
- 部分网站使用高级 Bot 检测（如 Cloudflare Turnstile），可能触发拦截
- 无头模式默认开启；如需可见浏览器，传入
headless=False - 下载文件依赖浏览器配置的下载路径
已支持功能
- ✅ 文件上传（
input[type=file]元素） - ✅ 文件下载（等待下载事件）
- ✅ 多标签页管理（open/switch/close tab）
- ✅ 反检测（stealth 模式，随机 User-Agent，人类速度）
- ✅ 截图 / 全页截图
- ✅ 表单填写 / 点击 / 滚动 / 悬停
- ✅ 文本提取 / HTML 提取
- ✅ 等待元素出现
What ships with it
6 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.
- 12d ago First seen · 136 lines · 54 tokens per session scan A a82962c83b51
browser-pilot is a skill published in the GitHub repository xyva-yuangui/XyvaClaw (21 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 970 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 2026-08-30.
Other skills, from other repositories
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.