How do I install the Browser Agent skill?

Run npx skillmds@latest add shanmukhaditya/browser-agent 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 Browser Agent 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 Browser Agent?

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 Browser Agent free to use?

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

Who published Browser Agent?

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

Browser Agent by shanmukhaditya — Agent Skill

Name: Browser Agent
Author: shanmukhaditya

Browser Agent

Autonomous stealth browser automation agent powered by Playwright with ref-based accessibility targeting, persistent daemon architecture, and human-motor kinematics (Bézier curves, natural typing rhythms). Replaces heavy DOM-streaming tools with token-efficient ref snapshots and full anti-bot protection.

shanmukhaditya ff1f579 5 files · 45.4 KB Updated Sep 17, 2026

File contents

Stealth Browser Agent (`agent-browser`)

browser-agent is an autonomous browser driver built for AI agents. It combines high token efficiency with full anti-bot stealth protection (bypassing Cloudflare, DataDome, Akamai) using a persistent background daemon.

⚡ Core Architecture

Persistent Daemon: Maintains a long-lived browser session via a Unix domain socket (/tmp/agent_browser.sock) to eliminate cold-start startup overhead.
Token-Efficient Ref Snapshots: After each navigation or interaction, an accessibility snapshot is generated and saved to /tmp/browser_snapshot.yaml. Interactive elements are assigned concise ref IDs (e1, e2, e3...).
Human Motor Kinematics:
- Mouse: Moves along cubic Bézier curves with natural acceleration, deceleration, and micro-overshoots.
- Keyboard: Types with randomized keystroke cadences (50ms–160ms) and word pauses.
- Scroll: Inertial wheel scrolling with reading pauses.
Native Chrome Execution: Auto-detects and binds to /Applications/Google Chrome.app to provide genuine audio/video codecs, TLS JA3/JA4 fingerprints, and WebGL ANGLE hardware contexts.

🛠️ CLI Commands Overview

All commands are executed via the agent-browser binary located at: ~/.gemini/config/skills/browser-agent/bin/agent-browser

# 1. Open a URL (starts daemon automatically)
agent-browser open "https://example.com"
agent-browser open "https://example.com" --headless

# 2. Inspect current interactive elements
agent-browser snapshot

# 3. Click an element using its ref ID
agent-browser click e3

# 4. Fill or type into form fields
agent-browser fill e1 "username@domain.com"
agent-browser type e2 "securePassword123"

# 5. Press special keys
agent-browser press Enter
agent-browser press Tab

# 6. Smooth human scrolling
agent-browser scroll --down 500
agent-browser scroll --up 300

# 7. Capture visual proof
agent-browser screenshot --output "/tmp/screenshot.png"

# 8. Run custom JavaScript evaluation
agent-browser eval "document.title"

# 9. Clean shutdown
agent-browser close

📋 Recommended Agent Workflow

When given a browser browsing, research, or form submission task:

Navigate to the target:

agent-browser open "https://target-website.com"

Inspect the Snapshot: Read /tmp/browser_snapshot.yaml (or view the returned JSON) to find the ref IDs for the elements you need.
Interact with Ref IDs: Execute agent-browser click <ref>, agent-browser fill <ref> <text>, or agent-browser press Enter.
Extract Information: Use agent-browser eval for direct DOM data or re-run agent-browser snapshot after page transitions.
Close when Finished: Run agent-browser close to free memory and shut down the daemon.

---name: browser-agentdescription: Autonomous stealth browser automation agent powered by Playwright with ref-based accessibility targeting, persistent daemon architecture, and human-motor kinematics (Bézier curves, natural typing rhythms). Replaces heavy DOM-streaming tools with token-efficient ref snapshots and full anti-bot protection.---# Stealth Browser Agent (`agent-browser`)`browser-agent` is an autonomous browser driver built for AI agents. It combines high token efficiency with full anti-bot stealth protection (bypassing Cloudflare, DataDome, Akamai) using a persistent background daemon.---## ⚡ Core Architecture1. **Persistent Daemon**: Maintains a long-lived browser session via a Unix domain socket (`/tmp/agent_browser.sock`) to eliminate cold-start startup overhead.2. **Token-Efficient Ref Snapshots**: After each navigation or interaction, an accessibility snapshot is generated and saved to `/tmp/browser_snapshot.yaml`. Interactive elements are assigned concise ref IDs (`e1`, `e2`, `e3`...).3. **Human Motor Kinematics**: - **Mouse**: Moves along cubic Bézier curves with natural acceleration, deceleration, and micro-overshoots. - **Keyboard**: Types with randomized keystroke cadences (50ms–160ms) and word pauses. - **Scroll**: Inertial wheel scrolling with reading pauses.4. **Native Chrome Execution**: Auto-detects and binds to `/Applications/Google Chrome.app` to provide genuine audio/video codecs, TLS JA3/JA4 fingerprints, and WebGL ANGLE hardware contexts.---## 🛠️ CLI Commands OverviewAll commands are executed via the `agent-browser` binary located at:`~/.gemini/config/skills/browser-agent/bin/agent-browser````bash# 1. Open a URL (starts daemon automatically)agent-browser open "https://example.com"agent-browser open "https://example.com" --headless# 2. Inspect current interactive elementsagent-browser snapshot# 3. Click an element using its ref IDagent-browser click e3# 4. Fill or type into form fieldsagent-browser fill e1 "username@domain.com"agent-browser type e2 "securePassword123"# 5. Press special keysagent-browser press Enteragent-browser press Tab# 6. Smooth human scrollingagent-browser scroll --down 500agent-browser scroll --up 300# 7. Capture visual proofagent-browser screenshot --output "/tmp/screenshot.png"# 8. Run custom JavaScript evaluationagent-browser eval "document.title"# 9. Clean shutdownagent-browser close```---## 📋 Recommended Agent WorkflowWhen given a browser browsing, research, or form submission task:1. **Navigate to the target**: ```bash agent-browser open "https://target-website.com" ```2. **Inspect the Snapshot**: Read `/tmp/browser_snapshot.yaml` (or view the returned JSON) to find the ref IDs for the elements you need.3. **Interact with Ref IDs**: Execute `agent-browser click <ref>`, `agent-browser fill <ref> <text>`, or `agent-browser press Enter`.4. **Extract Information**: Use `agent-browser eval` for direct DOM data or re-run `agent-browser snapshot` after page transitions.5. **Close when Finished**: Run `agent-browser close` to free memory and shut down the daemon.

Frequently asked questions