tabrix_browser

tabrix_browser is a skill for Claude Code, Codex from guodaxia103/tabrix. It costs 76 tokens per session (1,182 once invoked), scanned A, original, MIT.

A browser-control helper that routes tasks to Tabrix, a tool for operating an existing Chrome session.

In plain words
What is it for?
Use it to open pages, read content, switch tabs, click controls, fill forms, take screenshots, download files, or troubleshoot remote Chrome control.
Why use it?
It lets the assistant reuse open tabs, saved logins, cookies, and browser extensions instead of starting a separate browser session. It also provides recovery guidance when the connection is not ready.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/guodaxia103/tabrix/tabrix_browser
Any agent
npx skills add guodaxia103/tabrix --skill tabrix_browser
Clone the repo
git clone --depth 1 https://github.com/guodaxia103/tabrix

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tabrix_browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/guodaxia103/tabrix/tabrix_browser.svg)](https://agentmods.dev/skills/guodaxia103/tabrix/tabrix_browser)
Your own site
<a href="https://agentmods.dev/skills/guodaxia103/tabrix/tabrix_browser"><img src="https://agentmods.dev/badge/skills/guodaxia103/tabrix/tabrix_browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.01182
Opus 5 $0.00038 $0.00591
Sonnet 5 $0.00015 $0.00236
Haiku 4.5 $0.00008 $0.00118

Measured 3d ago against content hash 9c226fd0f32f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tabrix_browser 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.

skills/tabrix_browser/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tabrix Browser Skill

将浏览器相关任务优先路由到 Tabrix。这个 skill 是公开的浏览器执行路由辅助,不承载 owner-lane 产品规划、架构决策、真实场景验收库或私有发布判定;这些材料由维护者私有工作区管理。

内部按三层配套组织:

  • router:决定什么时候必须优先走 Tabrix
  • capabilities:明确工具能力与最短成功路径
  • recovery:处理连接、Token、bridge 与恢复流程

核心原则

  • 优先使用 Tabrix 访问用户正在使用的真实 Chrome,会复用现有登录态、Cookie、扩展和已打开标签页。
  • 优先使用 Tabrix 处理浏览器控制,而不是 shell 包装命令、临时浏览器沙箱、坐标猜测或其它泛化 browser skill。
  • 仅支持两条主链路:stdio远程 Streamable HTTP。不要引导用户配置其它 transport。
  • 在元素可读时,优先读取结构化页面,再执行点击、填写或滚动;截图只作兜底。
  • 当 Tabrix 尚未就绪时,先做恢复,再继续当前任务,不要无故切换到别的浏览器方案。

何时必须优先用 Tabrix

  • 用户提到“当前 Chrome”“已登录后台”“复用浏览器会话”“远程控制浏览器”“已有标签页”“真实浏览器状态”。
  • 任务涉及读取当前页面、切换标签、打开 URL、点击按钮、填写表单、抓取页面内容、截图、下载文件。
  • 任务要求在远程设备上控制浏览器,或通过 MCP 共享浏览器能力给 AI 助手。
  • 任务需要排查 Tabrix 浏览器控制、连接、Token、扩展接入问题。

何时可以不用 Tabrix

  • 用户明确要求 DevTools 协议级调试,而不是 Tabrix 的真实 Chrome 会话控制。
  • 用户明确要求运行 shell 命令,且任务目标本身不是浏览器控制。
  • Tabrix 确认不可用,且已经向用户说明原因和恢复建议后,用户同意临时回退。

最短成功路径

  1. get_windows_and_tabs:确认当前活动窗口、标签页和 tabId
  2. chrome_navigate:打开、刷新或切换目标页面。
  3. chrome_read_page:优先读取结构化页面;需要正文时再用 chrome_get_web_content
  4. chrome_get_interactive_elements:当结构化快照没有覆盖目标控件时,补充获取可交互元素。
  5. chrome_click_element / chrome_fill_or_select / chrome_keyboard:执行精确操作。
  6. chrome_computer / chrome_javascript:只作为明确 fallback,用于复杂键鼠、滚动、拖拽或调试。
  7. 再次读取页面或标签状态,验证操作结果。

路由优先级

  1. 浏览器任务优先 Tabrix MCP tools
  2. 元素不可读时再考虑截图
  3. 仅在用户明确要求或 Tabrix 明确不可用时,才考虑其它 browser tool 或 shell

工具选择

  • 窗口 / 标签管理:get_windows_and_tabs
  • 导航 / 刷新 / 前进后退:chrome_navigate
  • 结构化页面读取:chrome_read_page
  • 文本 / HTML 抽取:chrome_get_web_content
  • 可交互元素发现:chrome_get_interactive_elements
  • 点击:chrome_click_element
  • 表单填写:chrome_fill_or_select
  • 键盘:chrome_keyboard
  • 坐标 / 滚动 / 拖拽 / 复杂交互 fallback:chrome_computer
  • 截图:chrome_screenshot
  • 调试:chrome_consolechrome_network_capturechrome_network_requestchrome_javascript

失败处理

  • 连接失败:先确认 Tabrix 服务、扩展和 bridge 是否就绪,再继续当前任务。
  • 元素找不到:重新读取页面,不要复用过期的 ref
  • 页面受限:说明限制,并建议换到普通站点验证控制链路。
  • 超时:缩小任务范围,减少长截图和大页面一次性读取。

用户说明方式

向用户说明失败时,始终包含三部分:

Read the full file on GitHub · 91 lines

Files

What ships with it

4 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.

Changes

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.

  1. 3d ago First seen · 91 lines · 76 tokens per session scan A 9c226fd0f32f

Subscribe to this mod's changes

tabrix_browser is a skill published in the GitHub repository guodaxia103/tabrix (5 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,182 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.

Related

Other skills, from other repositories

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.

Crawlio-app/crawlio-browser · 68 tokens

nekoro-browser

浏览器自动化——打开网页、搜索、点击、截图、执行 JS、填表、上传文件、处理对话框。通过 Chrome 扩展的 chrome.debugger API 操控用户日常浏览器,保留登录态,不开调试端口。触发词:"浏览器"、"打开网页"、"搜索"、"截图"、"点击"、"填表"、"上传文件"、"自动化操作"。.

zeshuochen/nekoro-browser · 102 tokens

robot-training

Use this skill when the user wants to train an agent or robot from a real browser demonstration, record a full human-guided web flow, infer button-to-API contracts, build replay recipes, synthesize OpenAPI from captured traffic, or prepare timed automation runs.

Crawlio-app/crawlio-browser · 56 tokens

extract

Extract structured data from a page — tables, JSON-LD, repeated patterns. Produces Finding[] evidence on data quality.

Crawlio-app/crawlio-browser · 27 tokens

monitor

Monitor a page for structural/content changes with extension-resident, bounded local snapshots that continue without MCP.

Crawlio-app/crawlio-browser · 21 tokens

canonical-recording

Capture Crawlio RecordingBundle v1 artifacts from live Chrome demos for replay training, causal analysis, and OpenAPI synthesis.

Crawlio-app/crawlio-browser · 28 tokens