Web Browser logo

Web Browser

CommunityPopular
mitsuhiko
web-browser

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

Overview

Publishermitsuhiko
Repositoryagent-stuff
Skill nameweb-browser
Stars
3.1K
Forks
224
Bundled files
18
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 18 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mitsuhiko on GitHub. Read the source before you install it.

Installation

Install the Web Browser AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mitsuhiko/agent-stuff.git /tmp/agent-stuff
mkdir -p .claude/skills
cp -r /tmp/agent-stuff/skills/web-browser .claude/skills/web-browser
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Web Browser in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Web Browser on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Web Browser is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Web Browser Skill

Minimal CDP tools for collaborative site exploration.

Start Chrome (Prefer Headless)

bash
./scripts/start.js --headless            # Recommended: isolated reusable profile
./scripts/start.js --headless --profile  # Headless with a copy of your profile
./scripts/start.js                       # Visible browser window when needed
./scripts/start.js --headless --reset-profile  # Clear cached profile before launch

Starts Chrome with remote debugging (default port :9222). Agents should use --headless by default because it is less disruptive and supports navigation, evaluation, screenshots, emulation, and logging. User extensions are disabled for headless launches; a copied profile still provides its cookies and other browser state, but extension-based features are unavailable. Headed launches continue to load extensions normally. Use headed mode only when a person needs to see or interact with the browser, such as for pick.js, manual authentication, or debugging a headless-specific difference.

The start script only reuses a running browser when its profile and launch settings match. Stop the running skill browser before switching between headless and headed mode. Changing the debugging port does not isolate the profile: startup refuses to modify a profile already used on another port and preserves Chrome's profile locks.

Profile behavior:

  • Default mode uses: ~/.cache/agent-web/browser/fresh-profile
  • --profile mode uses: ~/.cache/agent-web/browser/profile-copy
  • The skill does not attach to your live Chrome profile directly
  • If :9222 is already used by an unknown instance, start will fail instead of reusing it

If Chrome is installed in a non-standard location, set:

bash
BROWSER_BIN=/path/to/chrome ./scripts/start.js --headless

Optional debug endpoint override:

bash
BROWSER_DEBUG_PORT=9333 ./scripts/start.js --headless

Stop Chrome

bash
./scripts/stop.js                         # Stop skill Chrome on :9222
BROWSER_DEBUG_PORT=9333 ./scripts/stop.js  # Stop skill Chrome on :9333
./scripts/stop.js --all                   # Stop all skill Chrome instances

Works for headless and headed browsers. Only processes using the skill's cached profiles are stopped, not your regular Chrome. Shutdown preserves cookies and other cached state; it never force-kills Chrome. Stop before using --reset-profile.

To switch to a visible browser:

bash
./scripts/stop.js
./scripts/start.js

Navigate

bash
./scripts/nav.js https://example.com
./scripts/nav.js https://example.com --new

Navigate current tab or open new tab.

Device Emulation (Mobile)

bash
./scripts/emulate.js --list
./scripts/emulate.js iphone-14
./scripts/emulate.js pixel-7 --landscape
./scripts/emulate.js --reset

Set an active device emulation preference (viewport, DPR, touch, UA) for browser skill commands. Use --reset to clear.

Commands like nav.js, eval.js, pick.js, dismiss-cookies.js, and screenshot.js automatically apply the active preference.

Evaluate JavaScript

bash
./scripts/eval.js 'document.title'
./scripts/eval.js 'document.querySelectorAll("a").length'
./scripts/eval.js 'document.querySelector("button")?.click(); "clicked"'
./scripts/eval.js 'await Promise.resolve(document.title)'
./scripts/eval.js 'JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => ({ text: a.textContent.trim(), href: a.href })).filter(link => !link.href.startsWith("https://")))'

Execute JavaScript in the active tab. Input can be an expression or statement list; the console-style completion value is printed and promises/top-level await are awaited. Be careful with string escaping, best to use single quotes.

Screenshot

bash
./scripts/screenshot.js
./scripts/screenshot.js --full-page
./scripts/screenshot.js --device iphone-14
./scripts/screenshot.js --device pixel-7 --full-page

Takes a screenshot and returns a temp file path.

  • Default: current viewport
  • --full-page: captures full document height
  • --device <preset>: temporary mobile emulation for that screenshot only

Pick Elements

bash
./scripts/pick.js "Click the submit button"

Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish. This requires headed Chrome; launch start.js without --headless.

Dismiss Cookie Dialogs

bash
./scripts/dismiss-cookies.js          # Accept cookies
./scripts/dismiss-cookies.js --reject # Reject cookies (where possible)

Automatically dismisses EU cookie consent dialogs.

Run after navigating to a page:

bash
./scripts/nav.js https://example.com && ./scripts/dismiss-cookies.js

Quick Mobile Debug Flow

bash
./scripts/start.js --headless
./scripts/nav.js https://example.com
./scripts/emulate.js iphone-14
./scripts/nav.js https://example.com      # reload with mobile UA
./scripts/dismiss-cookies.js
./scripts/screenshot.js --full-page

Background Logging (Console + Errors + Network)

Automatically started by start.js and writes JSONL logs to:

~/.cache/agent-web/logs/YYYY-MM-DD/<targetId>.jsonl

Manually start:

bash
./scripts/watch.js

Tail latest log:

bash
./scripts/logs-tail.js           # dump current log and exit
./scripts/logs-tail.js --follow  # keep following

Summarize network responses:

bash
./scripts/net-summary.js

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Web Browser AI skill do?

Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.

Why use Web Browser on TypingMind?

Because you install it once and use it with any model. Web Browser is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Web Browser in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mitsuhiko/agent-stuff/tree/main/skills/web-browser. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Web Browser?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Web Browser?

As many as you like. As long as a model supports skills, you can use Web Browser with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Web Browser AI skill free?

Yes. It is published on GitHub by mitsuhiko under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇