How do I install the Agent Browser skill?

Run npx skillmds@latest add chainlesschain/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. This skill is licensed under MIT.

Who published Agent Browser?

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

Agent Browser by chainlesschain — Agent Skill

Name: Agent Browser
Author: chainlesschain

Agent Browser

Advanced browser automation for AI agents with snapshot-ref interaction pattern - navigate, snapshot interactive elements with refs, click/fill/select by refs, manage sessions, and extract structured data

chainlesschain f2960e3 2 files · 12.9 KB Updated Sep 17, 2026

File contents

Agent Browser Skill

Advanced browser automation using the snapshot-ref interaction pattern.

Core Workflow

Every browser automation follows this pattern:

Navigate: open <url>
Snapshot: Get interactive elements with refs (@e1, @e2, ...)
Interact: Use refs to click, fill, select
Re-snapshot: After DOM changes, get fresh refs

/agent-browser open https://example.com
/agent-browser snapshot
# Output: @e1 [input email], @e2 [input password], @e3 [button] "Login"
/agent-browser fill @e1 "user@example.com"
/agent-browser fill @e2 "secret"
/agent-browser click @e3
/agent-browser snapshot   # Check result

Commands

Command	Description	Example
`open`	Navigate to URL	`open https://example.com`
`snapshot`	Get interactive elements with refs	`snapshot`
`click`	Click element by ref	`click @e1`
`fill`	Clear and type into element	`fill @e2 "text"`
`type`	Type without clearing	`type @e2 "text"`
`select`	Select dropdown option	`select @e3 "option"`
`screenshot`	Capture page screenshot	`screenshot`
`extract`	Extract text/data from element	`extract @e5`
`wait`	Wait for element or condition	`wait @e1` or `wait 2000`

Session Management

/agent-browser session-save auth.json     # Save cookies/state
/agent-browser session-load auth.json     # Restore state

Common Patterns

Form Submission

open https://example.com/signup → snapshot → fill fields → click submit → snapshot

Data Extraction

open <url> → snapshot → extract @e5 → extract body

Multi-Page Navigation

open <url> → snapshot → click @link → wait → snapshot → repeat

Element Refs

Refs like @e1, @e2 are assigned by snapshot to interactive elements
Refs are reset on each new snapshot
Use descriptive selectors as fallback: click "Login button"

---name: agent-browserdescription: Advanced browser automation for AI agents with snapshot-ref interaction pattern - navigate, snapshot interactive elements with refs, click/fill/select by refs, manage sessions, and extract structured datalicense: MIT---# Agent Browser SkillAdvanced browser automation using the snapshot-ref interaction pattern.## Core WorkflowEvery browser automation follows this pattern:1. **Navigate**: `open <url>`2. **Snapshot**: Get interactive elements with refs (`@e1`, `@e2`, ...)3. **Interact**: Use refs to click, fill, select4. **Re-snapshot**: After DOM changes, get fresh refs```/agent-browser open https://example.com/agent-browser snapshot# Output: @e1 [input email], @e2 [input password], @e3 [button] "Login"/agent-browser fill @e1 "user@example.com"/agent-browser fill @e2 "secret"/agent-browser click @e3/agent-browser snapshot # Check result```## Commands| Command | Description | Example || --- | --- | --- || `open` | Navigate to URL | `open https://example.com` || `snapshot` | Get interactive elements with refs | `snapshot` || `click` | Click element by ref | `click @e1` || `fill` | Clear and type into element | `fill @e2 "text"` || `type` | Type without clearing | `type @e2 "text"` || `select` | Select dropdown option | `select @e3 "option"` || `screenshot` | Capture page screenshot | `screenshot` || `extract` | Extract text/data from element | `extract @e5` || `wait` | Wait for element or condition | `wait @e1` or `wait 2000` |## Session Management```/agent-browser session-save auth.json # Save cookies/state/agent-browser session-load auth.json # Restore state```## Common Patterns### Form Submission```open https://example.com/signup → snapshot → fill fields → click submit → snapshot```### Data Extraction```open <url> → snapshot → extract @e5 → extract body```### Multi-Page Navigation```open <url> → snapshot → click @link → wait → snapshot → repeat```## Element Refs- Refs like `@e1`, `@e2` are assigned by snapshot to interactive elements- Refs are reset on each new snapshot- Use descriptive selectors as fallback: `click "Login button"`

Frequently asked questions