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 LinVireo/browsertap-mcp --skill browsertap-bridge-recoverygit clone --depth 1 https://github.com/LinVireo/browsertap-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/skills/linvireo/browsertap-mcp/browsertap-bridge-recovery)<a href="https://agentmods.dev/skills/linvireo/browsertap-mcp/browsertap-bridge-recovery"><img src="https://agentmods.dev/badge/skills/linvireo/browsertap-mcp/browsertap-bridge-recovery/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/linvireo/browsertap-mcp/browsertap-bridge-recovery"><img src="https://agentmods.dev/badge/skills/linvireo/browsertap-mcp/browsertap-bridge-recovery.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 | $0.00086 | $0.03429 |
| Opus 5 | $0.00043 | $0.01715 |
| Sonnet 5 | $0.00017 | $0.00686 |
| Haiku 4.5 | $0.00009 | $0.00343 |
Grade A, and why
browsertap-bridge-recovery 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 2d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BTAP 连接与恢复
本 skill 写给正在调用 BTAP、需要恢复连接的 agent。 正常任务执行和标签页清理见 [[browsertap-default]]； 安装与完整人工操作见故障排查。 修改产品源码的任务另读仓库 AGENTS.md / CONTRIBUTING.md。
先判定，再操作
- 保存失败工具、目标
session_id、error_code、delivery_state和operation_id。有未知执行先补查，不把恢复连接当成可以重放的证明。 - 运行安装环境中的
browsertap doctor；MCP 仍响应时也可用get_setup_status。 使用实际安装的可执行文件路径，避免诊断到另一个 Python 环境。 - 按
action处理对应组件。没有明确结论时，再按“端口、HTTP、MCP”逐层检查。 - 恢复后先验证
list_tabs和目标身份，再恢复业务操作。记录未知结果与尚需人工完成的动作。
action / 证据 |
对应处理 |
|---|---|
none / healthy |
通道正常；检查原工具或页面层，不重启。 |
wait_for_extension / starting |
bridge 刚启动，给扩展重连时间，再做一次有界检查。 |
restart_mcp_session / stale_package |
重启该 MCP 会话，使其加载新包与工具 schema；不是重启浏览器。 |
restart_bridge / stale_bridge |
确认影响范围后用 browsertap bridge --restart。 |
reload_extension / stale_extension |
请求用户在对应浏览器的扩展页手动 Reload BrowserTap Bridge。 |
check_config / initialization_failed |
先纠正报告中的配置或解释器问题，不把它当运行中的桥宕机。 |
bridge 由多个 MCP 会话共享。重启前说明会影响这些会话，且不会取消已经在浏览器执行的 JS。
browsertap bridge 不带参数会前台常驻；日常恢复使用管理子参数，
只有明确需要前台调试时才运行裸命令。
构建身份
MCP server、常驻 bridge 和 MV3 扩展分别加载代码。更新包后要检查各自的运行身份，
不能只比较 get_setup_status.package_version 与扩展 manifest 版本。
extension_build_verdict |
结论 |
|---|---|
matches_tree |
运行 worker 与当前扩展源码一致；仅版本号差异不要求 Reload。 |
stale_worker |
运行 worker 与源码不同，需要人工 Reload。 |
stamp_not_regenerated |
源码与生成的 stamp 不一致，应交给源码维护者处理，不能靠 Reload 证明新旧。 |
unverifiable |
未能比较，不是通过。 |
extension_build_enforced=false 同样表示没有执行比较。
源码维护者修改扩展后运行 python -m scripts.extension_stamp --write，
再由用户 Reload；调用方不要为消除诊断而自行改 stamp。
matches_tree 也不免除协议版本或必需 capability 的真实缺口。
chrome.runtime.reload() 不是项目认可的磁盘源码更新验证方法。
BTAP 不允许自动禁用自身来强制刷新；被禁用后它无法重新启用自己。
分层检查
默认 bridge 使用 WebSocket 18765、HTTP 18766；自定义地址/端口以 doctor 报告为准。 扩展 WebSocket 检查 origin，HTTP 使用共享 Bearer token，是两条不同通道。
| 检查 | 成功能证明什么 | 失败后看哪里 |
|---|---|---|
| 对应端口在 LISTENING | 有进程监听，不代表一定是 BTAP | 核对 PID、进程命令行和配置端口。 |
认证的 /link 只读请求返回正确结构 |
bridge 的 HTTP handler 可用 | HTTP 状态、token 配置、进程日志。 |
get_all_sessions 返回预期标签页 |
bridge 收到了扩展的页面注册 | 空列表时继续查浏览器/扩展，不先重装客户端。 |
MCP list_tabs 返回 |
MCP 客户端到 bridge 的路径可用 | 只有 MCP 失败时定位该客户端会话。 |
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.
- 2d ago Changed · -123 lines · +86 tokens per session 6d468d3bb3c8
- 11d ago First seen · 331 lines · 0 tokens per session scan A d0868c7f29b1
browsertap-bridge-recovery is a skill published in the GitHub repository LinVireo/browsertap-mcp (2 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 3,429 once invoked, about $0.0004 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
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
browser-automation
Use this skill when the user asks to interact with a browser, take screenshots, inspect a page, capture network traffic, detect frameworks, click elements, fill forms, record browser sessions, or automate any browser task. Orchestrates Crawlio Browser's 150 browser tools via the search + execute + connecttab interface.
web-research
Structured web research, site audits, and competitive analysis. Acquire → Normalize → Analyze protocol with Evidence Mode findings.
clone
Capture a site's design system — colors, typography, spacing, layout, components — as structured findings.
compare
Side-by-side comparison of two websites across 11 dimensions. Produces Finding[] evidence per dimension.
dossier
Competitive intelligence dossier — compare a target against 2-4 competitors across all dimensions.