Agent Browser

OrganizationPopular

sipeed

agent-browser

Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.

Overview

Publisher	sipeed
Repository	`picoclaw`
Skill name	`agent-browser`
Stars	30K
Forks	4.5K
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by sipeed on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/sipeed/picoclaw.git /tmp/picoclaw
mkdir -p .claude/skills
cp -r /tmp/picoclaw/workspace/skills/agent-browser .claude/skills/agent-browser

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent 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 Agent 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 Agent 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.

Agent Browser

CLI browser automation via Chrome/Chromium CDP. Install: npm i -g agent-browser && agent-browser install.

Before using this skill, verify the tool is available by running which agent-browser. If the command is not found, tell the user that browser automation requires the agent-browser CLI and Chromium, which are only available in the heavy container image. Do not attempt to install it at runtime.

Core Workflow

agent-browser open <url> — navigate
agent-browser snapshot -i — get interactive elements with refs (@e1, @e2, ...)
Interact using refs — click @e1, fill @e2 "text"
Re-snapshot after any navigation or DOM change — refs are invalidated

bash
agent-browser open https://example.com/form
agent-browser snapshot -i
# @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "secret"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i

Chain commands with && when you don't need intermediate output:

bash
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

Commands

bash
# Navigation
agent-browser open <url>
agent-browser close

# Snapshot
agent-browser snapshot -i                # Interactive elements with refs
agent-browser snapshot -s "#selector"    # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1
agent-browser fill @e2 "text"            # Clear + type
agent-browser type @e2 "text"            # Type without clearing
agent-browser select @e1 "option"
agent-browser check @e1
agent-browser press Enter
agent-browser scroll down 500

# Get info
agent-browser get text @e1
agent-browser get url
agent-browser get title

# Wait
agent-browser wait @e1                   # Wait for element
agent-browser wait --load networkidle    # Wait for network idle
agent-browser wait --url "**/dashboard"  # Wait for URL pattern
agent-browser wait --text "Welcome"      # Wait for text
agent-browser wait 2000                  # Wait ms

# Capture
agent-browser screenshot                 # Screenshot to temp dir
agent-browser screenshot --full          # Full page
agent-browser screenshot --annotate      # With numbered element labels ([N] -> @eN)
agent-browser pdf output.pdf

# Semantic locators (when refs unavailable)
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"

Authentication

bash
# Option 1: Import from user's running Chrome
agent-browser --auto-connect state save ./auth.json
agent-browser --state ./auth.json open https://app.example.com

# Option 2: Persistent profile
agent-browser --profile ~/.myapp open https://app.example.com/login
# ... login once, all future runs are authenticated

# Option 3: Session name (auto-save/restore)
agent-browser --session-name myapp open https://app.example.com/login
# ... login, close, next run state is restored

# Option 4: State file
agent-browser state save auth.json
agent-browser state load auth.json

Iframes

Iframe content is inlined in snapshots. Interact with iframe refs directly — no frame switch needed.

Parallel Sessions

bash
agent-browser --session s1 open https://site-a.com
agent-browser --session s2 open https://site-b.com
agent-browser session list

JavaScript Eval

bash
agent-browser eval 'document.title'

# Complex JS — use --stdin to avoid shell quoting issues
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => a.href))
EVALEOF

Cleanup

Always close sessions when done:

bash
agent-browser close
agent-browser --session s1 close

Frequently asked questions

What does the Agent Browser AI skill do?

Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.

Why use Agent Browser on TypingMind?

Because you install it once and use it with any model. Agent 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 Agent Browser in TypingMind?

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

Which AI models can use Agent 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 Agent Browser?

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

Is the Agent Browser AI skill free?

Yes. It is published on GitHub by sipeed under the MIT 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

To Spec

mattpocock

CommunityPopular

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

To Tickets

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket…

Triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Claude Handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Agent Browser

Core Workflow

Commands

Authentication

Iframes

Parallel Sessions

JavaScript Eval

Cleanup

Frequently asked questions

Related AI Skills

Set up your own AI workspace now