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/uu201/character-arc/browser-cdpnpx skills add uu201/character-arc --skill browser-cdpgit clone --depth 1 https://github.com/uu201/character-arcWhat 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 | $0.00094 | $0.01442 |
| Opus 5 | $0.00047 | $0.00721 |
| Sonnet 5 | $0.00019 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
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 3d 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 — 141 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 12+
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
1 file 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.
- 3d ago First seen · 141 lines · 94 tokens per session scan A 8f9e48684bf9
browser-cdp is a skill published in the GitHub repository uu201/character-arc (534 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,442 once invoked, about $0.0005 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
omh-browser
This is a Hermes-native browser-operator workflow skill.
octocode-chrome-devtools
Use when a live page needs Chrome DevTools/CDP evidence: network failures, console errors, performance, DOM/CSS actionability, screenshots/PDF, cookies/storage, click/fill/search, HAR, or auth-gated pages. Phrases like debug in Chrome, live page health, CDP snapshot, cookie bridge. Not for static crawl or bulk extract…
e2e-verify
面向 Bifrost 管理端的端到端 UI 与 API 验证工具。 适用于浏览器测试、场景回归、管理端接口验证与页面快照排查。 Use when: 端到端验证、功能验证、E2E 测试、UI 测试、浏览器测试、API 测试、接口验证.
site-cookie-login
Open a target website, wait for user login, verify login with required cookies plus an HTTP probe, and save cookies into .env for later automation. Use this when a site needs controlled browser login, cookie persistence, and automatic login-state checks.
agent-browser
Use when an agent needs real browser automation for semantic element targeting, form interaction, screenshots, recordings, script execution, session reuse, or end-to-end web workflow verification.
ppt-orchestrator
统一 PPT / 演示文稿 / 长图 / 周报 调度器。从ppt 出图法 V2 7 步，到 6 种风格字典（商务科技/博物图鉴/手绘科教/真实生活感/城市插画/反套路金句），到输出形式决策（HTML 阅读器 / 真实 .pptx / McKinsey HTML / huashu-design / design-master），下游分发到对应 skill 执行。Triggers：做 PPT / 做个演示 / 演示文稿 / 打包成 HTML / 真实 .pptx / 周报长图 / 卡脖子分析长图 / 幻灯片 / presentation / slides / deck。.