How do I install the Agent Browser skill?

Run npx skillmds@latest add matrixy/agent-browser in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Browser safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Browser?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Browser free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Browser?

matrixy (@matrixy) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Browser by matrixy — Agent Skill

Name: Agent Browser
Author: matrixy

Agent Browser

Headless browser automation CLI optimized for AI agents. Use when automating multi-step browser workflows, web scraping, form filling, or testing SPAs. Uses accessibility tree snapshots with ref-based element selection for deterministic actions. Requires `agent-browser` CLI (npm install -g agent-browser).

matrixy Updated Sep 17, 2026

File contents

Agent Browser Skill

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

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

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

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 --load networkidle     # Wait for network

Sessions (Isolated Browsers)

agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list

State Persistence

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

Screenshots

agent-browser screenshot page.png
agent-browser screenshot --full page.png  # Full page

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

Always use -i flag - Focus on interactive elements
Always use --json - Easier to parse
Wait for stability - agent-browser wait --load networkidle
Save auth state - Skip login flows with state save/load
Use sessions - Isolate different browser contexts

Example: Form Automation

agent-browser open https://example.com/form
agent-browser snapshot -i --json
# AI identifies: @e2=name, @e3=email, @e4=submit
agent-browser fill @e2 "John Doe"
agent-browser fill @e3 "john@example.com"
agent-browser click @e4
agent-browser wait --text "Success"

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

---name: agent-browserdescription: Headless browser automation CLI optimized for AI agents. Use when automating multi-step browser workflows, web scraping, form filling, or testing SPAs. Uses accessibility tree snapshots with ref-based element selection for deterministic actions. Requires `agent-browser` CLI (npm install -g agent-browser).---# Agent Browser SkillFast browser automation using accessibility tree snapshots with refs for deterministic element selection.## Core Workflow```bash# 1. Navigate and snapshotagent-browser open https://example.comagent-browser snapshot -i --json# 2. Parse refs from JSON, then interactagent-browser click @e2agent-browser fill @e3 "text"# 3. Re-snapshot after page changesagent-browser snapshot -i --json```## Key Commands### Navigation```bashagent-browser open <url>agent-browser back | forward | reload | close```### Snapshot (Always use -i --json)```bashagent-browser snapshot -i --json # Interactive elements, JSON outputagent-browser snapshot -i -c -d 5 --json # + compact, depth limitagent-browser snapshot -s "#main" -i # Scope to selector```### Interactions (Ref-based)```bashagent-browser click @e2agent-browser fill @e3 "text"agent-browser type @e3 "text"agent-browser hover @e4agent-browser check @e5 | uncheck @e5agent-browser select @e6 "value"agent-browser press "Enter"agent-browser scroll down 500```### Get Information```bashagent-browser get text @e1 --jsonagent-browser get html @e2 --jsonagent-browser get value @e3 --jsonagent-browser get attr @e4 "href" --jsonagent-browser get title --jsonagent-browser get url --json```### Check State```bashagent-browser is visible @e2 --jsonagent-browser is enabled @e3 --jsonagent-browser is checked @e4 --json```### Wait```bashagent-browser wait @e2 # Wait for elementagent-browser wait 1000 # Wait msagent-browser wait --text "Welcome" # Wait for textagent-browser wait --load networkidle # Wait for network```### Sessions (Isolated Browsers)```bashagent-browser --session admin open site.comagent-browser --session user open site.comagent-browser session list```### State Persistence```bashagent-browser state save auth.json # Save cookies/storageagent-browser state load auth.json # Load (skip login)```### Screenshots```bashagent-browser screenshot page.pngagent-browser screenshot --full page.png # Full page```## Snapshot Output Format```json{ "success": true, "data": { "snapshot": "...", "refs": { "e1": {"role": "heading", "name": "Example Domain"}, "e2": {"role": "button", "name": "Submit"}, "e3": {"role": "textbox", "name": "Email"} } }}```## Best Practices1. **Always use `-i` flag** - Focus on interactive elements2. **Always use `--json`** - Easier to parse3. **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## Example: Form Automation```bashagent-browser open https://example.com/formagent-browser snapshot -i --json# AI identifies: @e2=name, @e3=email, @e4=submitagent-browser fill @e2 "John Doe"agent-browser fill @e3 "john@example.com"agent-browser click @e4agent-browser wait --text "Success"```## Installation```bashnpm install -g agent-browseragent-browser install # Download Chromiumagent-browser install --with-deps # Linux: + system deps```## CreditsSkill created by Yossi Elkrief ([@MaTriXy](https://github.com/MaTriXy))agent-browser CLI by [Vercel Labs](https://github.com/vercel-labs/agent-browser)

Frequently asked questions