Skill: Agent Browser

Owner: matrixy

Summary: Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Tags: latest:0.1.0

Version history:

v0.1.0 | 2026-01-21T22:00:54.381Z | auto

• Initial release of agent-browser-clawdbot skill.
• Enables fast, headless browser automation via CLI, optimized for AI agent workflows.
• Provides accessibility tree snapshots with ref-based deterministic element selection.
• Supports session isolation, state persistence, and robust automation commands (navigation, interaction, data extraction, network control, and more).
• Includes example workflows and best practices for efficient automation.

Archive index:

Archive v0.1.0: 3 files, 3435 bytes

Files: skill-card.md (2089b), SKILL.md (5548b), _meta.json (141b)

File v0.1.0:SKILL.md

---

name: agent-browser description: Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection metadata: {"clawdbot":{"emoji":"🌐","requires":{"commands":["agent-browser"]},"homepage":"https://github.com/vercel-labs/agent-browser"}}

Agent Browser Skill

Fast browser automation using accessibility tree snapshots with refs for deterministic element selection.

Why Use This Over Built-in Browser Tool

Use agent-browser when:

• Automating multi-step workflows
• Need deterministic element selection
• Performance is critical
• Working with complex SPAs
• Need session isolation

Use built-in browser tool when:

• Need screenshots/PDFs for analysis
• Visual inspection required
• Browser extension integration needed

Core Workflow

# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json

# 2. Parse refs from JSON, then interact
agent-browser click @e2
agent-browser fill @e3 "text"

# 3. Re-snapshot after page changes
agent-browser snapshot -i --json

Key Commands

Navigation

agent-browser open <url>
agent-browser back | forward | reload | close

Snapshot (Always use -i --json)

agent-browser snapshot -i --json          # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json  # + compact, depth limit
agent-browser snapshot -s "#main" -i      # Scope to selector

Interactions (Ref-based)

agent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8

Get Information

agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --json

Check State

agent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --json

Wait

agent-browser wait @e2                    # Wait for element
agent-browser wait 1000                   # Wait ms
agent-browser wait --text "Welcome"       # Wait for text
agent-browser wait --url "**/dashboard"   # Wait for URL
agent-browser wait --load networkidle     # Wait for network
agent-browser wait --fn "window.ready === true"

Sessions (Isolated Browsers)

agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list
# Or via env: AGENT_BROWSER_SESSION=admin agent-browser ...

State Persistence

agent-browser state save auth.json        # Save cookies/storage
agent-browser state load auth.json        # Load (skip login)

Screenshots & PDFs

agent-browser screenshot page.png
agent-browser screenshot --full page.png
agent-browser pdf page.pdf

Network Control

agent-browser network route "**/ads/*" --abort           # Block
agent-browser network route "**/api/*" --body '{"x":1}'  # Mock
agent-browser network requests --filter api              # View

Cookies & Storage

agent-browser cookies                     # Get all
agent-browser cookies set name value
agent-browser storage local key           # Get localStorage
agent-browser storage local set key val

Tabs & Frames

agent-browser tab new https://example.com
agent-browser tab 2                       # Switch to tab
agent-browser frame @e5                   # Switch to iframe
agent-browser frame main                  # Back to main

Snapshot Output Format

{
  "success": true,
  "data": {
    "snapshot": "...",
    "refs": {
      "e1": {"role": "heading", "name": "Example Domain"},
      "e2": {"role": "button", "name": "Submit"},
      "e3": {"role": "textbox", "name": "Email"}
    }
  }
}

Best Practices

1. Always use -i flag - Focus on interactive elements
2. Always use --json - Easier to parse
3. Wait for stability - agent-browser wait --load networkidle
4. Save auth state - Skip login flows with state save/load
5. Use sessions - Isolate different browser contexts
6. Use --headed for debugging - See what's happening

Example: Search and Extract

agent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json

Example: Multi-Session Testing

# Admin session
agent-browser --session admin open app.com
agent-browser --session admin state load admin-auth.json
agent-browser --session admin snapshot -i --json

# User session (simultaneous)
agent-browser --session user open app.com
agent-browser --session user state load user-auth.json
agent-browser --session user snapshot -i --json

Installation

npm install -g agent-browser
agent-browser install                     # Download Chromium
agent-browser install --with-deps         # Linux: + system deps

Credits

Skill created by Yossi Elkrief (@MaTriXy)

agent-browser CLI by Vercel Labs

File v0.1.0:_meta.json

{ "ownerId": "kn7amrtkn0tjk2r2yxf3hjgp0s7zn6g4", "slug": "agent-browser-clawdbot", "version": "0.1.0", "publishedAt": 1769032854381 }

File v0.1.0:skill-card.md

Description: <br>

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection. <br>

This skill is ready for commercial/non-commercial use. <br>

Publisher: <br>

MaTriXy <br>

License/Terms of Use: <br>

Use Case: <br>

Developers and AI agents use this skill to automate browser workflows, inspect accessibility snapshots, select elements deterministically by reference, and extract page data through the agent-browser CLI. <br>

Deployment Geography for Use: <br>

Global <br>

Known Risks and Mitigations: <br>

Risk: Saved browser state and cookies can represent sensitive account access. <br> Mitigation: Keep saved authentication files out of source control and logs, and use isolated sessions or test accounts for automation. <br> Risk: The skill depends on the external agent-browser package source. <br> Mitigation: Install only when the package source is trusted and review commands before running them on logged-in websites. <br>

Reference(s): <br>

• Agent Browser upstream repository <br>
• ClawHub skill page <br>
• Publisher profile <br>

Skill Output: <br>

Output Type(s): [Text, Markdown, Shell commands, Configuration, Guidance] <br> Output Format: [Markdown with inline shell commands and JSON examples] <br> Output Parameters: [1D] <br> Other Properties Related to Output: [May guide browser state persistence, session isolation, navigation, interaction, data extraction, screenshots, PDFs, network control, cookies, and storage workflows.] <br>

Skill Version(s): <br>

0.1.0 (source: server release metadata) <br>

Ethical Considerations: <br>

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>