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 commands/deng1986/chrome-bridge-mcp/googlegit clone --depth 1 https://github.com/deng1986/chrome-bridge-mcpWrote 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/commands/deng1986/chrome-bridge-mcp/google)<a href="https://agentmods.dev/commands/deng1986/chrome-bridge-mcp/google"><img src="https://agentmods.dev/badge/commands/deng1986/chrome-bridge-mcp/google.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 | $0.00017 | $0.00603 |
| Opus 5 | $0.00009 | $0.00302 |
| Sonnet 5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
google 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.
What it actually says
目标
通过 chrome-bridge MCP 工具使用真实 Chrome 完成 Google 搜索和 Google AI 多轮讨论，不要求用户手工复制粘贴浏览器内容。
使用规则
用户可能用自然语言，也可能用 #g 前缀表达需求：
#g new <话题> 新开 Google AI 会话
#g <内容> 继续当前 Google AI 会话；没有当前会话时先新开
#g read 读取当前 Google AI 会话
#g export 导出当前 Google AI 会话
#g end 导出当前 Google AI 会话并关闭对应 Chrome 标签页
Google 搜索可以用自然语言表达，例如：
用 Google 搜索 <查询>
工具映射
- 搜索：优先调用
mcp__chrome-bridge__search_google_and_extract。 - Google AI 新会话：调用
mcp__chrome-bridge__start_google_ai_session。 - Google AI 追问：调用
mcp__chrome-bridge__continue_google_ai_session，通常省略sessionId，让 bridge 使用当前活跃会话。 - 读取当前会话：调用
mcp__chrome-bridge__read_google_ai_session，通常省略sessionId。 - 导出当前会话：调用
mcp__chrome-bridge__export_google_ai_session，通常省略sessionId。 - 结束当前会话：调用
mcp__chrome-bridge__end_google_ai_session，通常省略sessionId，默认关闭对应 Chrome 标签页。
标签页原则
同一件事尽量使用一个 Chrome 标签页完成。chrome-bridge 会维护当前 Google task tab；搜索和 Google AI 新入口会优先复用该标签页，只有标签页不存在或被用户手动关闭时才新开。
不要主动关闭用户手工打开的非 bridge 标签页。只有用户明确要求结束，或使用 #g end 时，才关闭 bridge 为当前会话登记的标签页。
人工接管
如果工具返回 needsUser=true、验证码、登录、同意条款、输入框不可用等状态：
- 告诉用户去 Chrome 中处理当前标签页。
- 说明处理完成后让用户回来继续。
- 用户回来后继续读取或追问同一个标签页，不要重新开页。
输出要求
- 只基于工具返回的 Google/页面内容回答。
- 不伪造搜索结果或 Google AI 回答。
- 回答中保留关键来源链接或报告路径。
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 · 57 lines · 17 tokens per session scan A c4b294984172
google is a command published in the GitHub repository deng1986/chrome-bridge-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 603 once invoked, about $0.0001 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 2026-09-01.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
can-i-use
Check browser support for web platform features against the project's browser targets.