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/djblack1209-coder/openclaw-bot/page-agentnpx skills add djblack1209-coder/OpenClaw-Bot --skill page-agentgit clone --depth 1 https://github.com/djblack1209-coder/OpenClaw-BotWrote 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/djblack1209-coder/openclaw-bot/page-agent)<a href="https://agentmods.dev/skills/djblack1209-coder/openclaw-bot/page-agent"><img src="https://agentmods.dev/badge/skills/djblack1209-coder/openclaw-bot/page-agent.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 | $0.00036 | $0.00705 |
| Opus 5 | $0.00018 | $0.00352 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
page-agent 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.
What it actually says
Page-Agent 浏览器 GUI 代理
阿里巴巴开源的网页内 GUI 代理,用自然语言控制浏览器界面。
核心优势
- 自然语言指令替代 CSS 选择器和 XPath
- 一行代码集成到现有项目
- 理解页面语义,不依赖 DOM 结构
- 比 Playwright 脚本更鲁棒(页面改版不会轻易失效)
安装
pip install page-agent
与 OpenClaw Bot 集成
替代当前 Playwright 社交发布
当前方式(Playwright 脚本,易碎):
await page.click('#post-button');
await page.fill('textarea.content', text);
await page.click('button[type="submit"]');
Page-Agent 方式(自然语言,鲁棒):
from page_agent import PageAgent
agent = PageAgent(page)
await agent.act("点击发布按钮")
await agent.act("在内容框中输入: " + text)
await agent.act("点击提交")
集成到社交发布流程
# tools/social-browser-adapter 升级
from page_agent import PageAgent
async def publish_to_x(content):
agent = PageAgent(browser_page)
await agent.act("点击撰写推文按钮")
await agent.act(f"输入推文内容: {content}")
await agent.act("点击发布按钮")
return await agent.act("确认推文已发布成功")
async def publish_to_xhs(content, images):
agent = PageAgent(browser_page)
await agent.act("点击发布笔记")
for img in images:
await agent.act(f"上传图片: {img}")
await agent.act(f"输入笔记内容: {content}")
await agent.act("点击发布")
使用场景
- 社交媒体发布 — 替代
social-browser-adapter.mjs中的 Playwright 硬编码 - 网页数据采集 — 替代
crawl4ai的部分场景 - 任意网页交互 — 严总 说"帮我在 xxx 网站上做 yyy"
触发条件
- 严总 说 "page-agent"、"自然语言控制浏览器"、"网页操作"
- 需要浏览器自动化但 Playwright 脚本太脆弱时
- 社交发布流程中 DOM 选择器失效时自动降级
与现有工具的关系
| 工具 | 适用场景 | 优势 |
|---|---|---|
| Playwright (当前) | 结构稳定的页面 | 速度快、精确 |
| Page-Agent (新增) | 页面结构不稳定 | 鲁棒、自然语言 |
| crawl4ai | 数据采集 | 专注提取 |
建议: Playwright 作为主路径,Page-Agent 作为降级方案和新页面的快速原型。
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 · 88 lines · 36 tokens per session scan A 7d2421ce2784
page-agent is a skill published in the GitHub repository djblack1209-coder/OpenClaw-Bot (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 705 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 2026-08-31.
Other skills, from other repositories
playwright-pom-discovery
Use when building or extending a Page Object Model (POM) for the Opik E2E suite (under testsendtoend/e2e/pom/) and you need to choose stable selectors against the live UI. Walks through seeding required state, exploring the running page with the Playwright MCP (accessibility snapshot + data-testid enumeration)…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
vellum-browser-use
Browse the web using assistant browser CLI commands.
macos-use
GUI control for macOS apps via mediar-ai's mcp-server-macos-use. Click, type, scroll, key-press, open apps — driven by accessibility tree, works in non-interactive Claude Code mode. Use this for any Sutando task that needs to drive another macOS application (Safari, Zoom, Mail, Finder, etc.).
restaurant-reservation
Book reservations on OpenTable or Resy with explicit confirmations.