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 leecyno1/boutique-skills --skill browser-cdpgit clone --depth 1 https://github.com/leecyno1/boutique-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/leecyno1/boutique-skills/browser-cdp)<a href="https://agentmods.dev/skills/leecyno1/boutique-skills/browser-cdp"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/browser-cdp/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/leecyno1/boutique-skills/browser-cdp"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/browser-cdp.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 | $0.00094 | $0.02056 |
| Opus 5.5 | $0.00038 | $0.00822 |
| Sonnet 5.5 | $0.00019 | $0.00411 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
browser-cdp 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 17d 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
100% identical to browser-cdp — 64 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser CDP 操作工具
通过 CDP 协议控制 Chrome，复用已有登录态，执行浏览器自动化操作。
前置条件
- macOS / Linux / Windows（实验性），已安装 Google Chrome
- Node.js 20+
agent-browser已安装：npm install -g agent-browser
⚠️ 首次启动会 kill 用户的常规 Chrome。 在启动前必须征求用户同意（见下方"启动流程"），否则用户可能丢失未保存的标签页/草稿。
启动流程（skill-mode 强制步骤）
第一步：探测当前状态（无副作用）
node {SKILL_DIR}/scripts/setup-cdp-chrome.js 9222 --detect-only
输出形如：
CDP_STATUS=ready # 已就绪，可直接复用
CDP_URL=http://127.0.0.1:9222/json/version
BROWSER=Chrome/148.0.7778.168
或：
CDP_STATUS=needs-setup
CHROME_RUNNING=yes # 用户有 Chrome 在跑，启动会杀掉
CHROME_PID_COUNT=3
第二步：根据探测结果分支
CDP_STATUS=ready→ 直接使用agent-browser --cdp 9222 ...，不要运行 setup。CDP_STATUS=needs-setup且CHROME_RUNNING=no→ 安全启动：node {SKILL_DIR}/scripts/setup-cdp-chrome.js 9222 --yesCDP_STATUS=needs-setup且CHROME_RUNNING=yes→ 先用 AskUserQuestion 工具向用户确认：告知会杀掉 N 个 Chrome 进程、可能丢失未保存工作；用户同意后再带--yes启动；用户拒绝则放弃这次自动化。
为什么不能直接 --yes： 脚本在非 TTY（即 skill 模式 / Bash 工具）下，如果检测到 Chrome 在跑而没有 --yes，会以退出码 3 报 NEEDS_CONSENT: ... 并中止，不会静默杀进程。这是有意的兜底——但 skill 流程仍应先问用户，而不是看到 3 就盲传 --yes。
启动脚本选项
| 选项 | 说明 |
|---|---|
--detect-only |
只探测，不修改任何状态（skill 用） |
--yes |
已征得同意，跳过交互提示 |
--reset |
启动前清空 ~/chrome-debug-profile（登录失效时用） |
--profile <name> |
使用非 Default 的 Chrome profile（如 "Profile 1"） |
--dry-run |
打印将执行的步骤，不执行 |
退出码：0 成功 / 1 通用错误 / 2 用户拒绝（TTY）/ 3 需同意但缺 --yes。
常用操作
打开页面并等待加载
agent-browser --cdp 9222 open "<URL>"
agent-browser --cdp 9222 wait 3000
提取页面文本
agent-browser --cdp 9222 eval 'document.body.innerText.substring(0, 8000)'
提取 Auth Token
agent-browser --cdp 9222 eval 'localStorage.getItem("token") || document.cookie'
复杂 JS（含引号 / $ / 反引号）
shell 转义容易出错，用以下两种方式之一：
# 1) base64 包裹
agent-browser --cdp 9222 eval -b "$(echo -n "document.querySelectorAll('a').length" | base64)"
# 2) heredoc + --stdin
cat <<'EOF' | agent-browser --cdp 9222 eval --stdin
const links = document.querySelectorAll('a');
links.length;
EOF
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.
- 17d ago First seen · 176 lines · 94 tokens per session scan A aa594fbec8ba
browser-cdp is a skill published in the GitHub repository leecyno1/boutique-skills (5 stars, last pushed 18d ago), licensed MIT. It adds 94 tokens to every session and 2,056 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to browser-cdp, differing in 64 lines, and is treated as a copy.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts with the existing agent-browser CLI, including screenshots and keyboard or interaction checks. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser automation.