Skill

Browser

Web browser automation with AI-optimized snapshots for claude-flow agents

Type: Skill
Repository: spencermarx/open-code-review
GitHub stars: 369
License: Apache-2.0
Repo last updated: Jul 28, 2026
Source file: .claude/skills/browser/SKILL.md
Version: 1.0.0

What Browser is

Browser is a skill published in the spencermarx/open-code-review repository on GitHub, which has about 369 stars. The repository describes itself as: “AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.”

A skill is a folder with a SKILL.md file: frontmatter with a name and a description, followed by instructions Claude follows. Claude loads a skill automatically when a task matches its description, and you can also run it directly with a slash and its name.

Skills work in Claude Code and in Claude Cowork, which makes Browser a portable way to give Claude the same method everywhere.

How to install Browser

Claude Code

Download the browser folder from the repository.
Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project.
Claude loads it automatically when a task matches; you can also run it with / and its name.

Claude Cowork

Zip the skill folder so SKILL.md sits at the top level of the folder.
Open Customize → Skills, click +, then upload the ZIP.
Start a task that matches the description, or call it by name with /.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from .claude/skills/browser/SKILL.md, shared under the repository's Apache-2.0 license. Read the full file on GitHub.

Web browser automation using agent-browser with AI-optimized snapshots. Reduces context by 93% using element refs (@e1, @e2) instead of full DOM.

Core Workflow

# 1. Navigate to page
agent-browser open <url>

# 2. Get accessibility tree with element refs
agent-browser snapshot -i    # -i = interactive elements only

# 3. Interact using refs from snapshot
agent-browser click @e2
agent-browser fill @e3 "text"

# 4. Re-snapshot after page changes
agent-browser snapshot -i

Quick Reference

Navigation

Snapshots (AI-Optimized)

Interaction

Get Info

Wait

Sessions

Selectors

Element Refs (Recommended)

# Get refs from snapshot
agent-browser snapshot -i
# Output: button "Submit" [ref=e2]

# Use ref to interact
agent-browser click @e2

CSS Selectors

agent-browser click "#submit"
agent-browser fill ".email-input" "[email protected]"

Semantic Locators

agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "[email protected]"
agent-browser find testid "login-btn" click

Examples

agent-browser open https://example.com/login
agent-browser snapshot -i
agent-browser fill @e2 "[email protected]"
agent-browser fill @e3 "password123"
agent-browser click @e4
agent-browser wait --url "**/dashboard"

Form Submission

agent-browser open https://example.com/contact
agent-browser snapshot -i
agent-browser fill @e1 "John Doe"
agent-browser fill @e2 "[email protected]"
agent-browser fill @e3 "Hello, this is my message"
agent-browser click @e4
agent-browser wait --text "Thank you"

Data Extraction

agent-browser open https://example.com/products
agent-browser snapshot -i
# Iterate through product refs
agent-browser get text @e1  # Product name
agent-browser get text @e2  # Price
agent-browser get attr @e3 href  # Link

Multi-Session (Swarm)

# Session 1: Navigator
agent-browser --session nav open https://example.com
agent-browser --session nav state save auth.json

# Session 2: Scraper (uses same auth)
agent-browser --session scrape state load auth.json
agent-browser --session scrape open https://example.com/data
agent-browser --session scrape snapshot -i

Integration with Claude Flow

MCP Tools

All browser operations are available as MCP tools with browser/ prefix:

browser/open
browser/snapshot
browser/click
browser/fill
browser/screenshot
etc.

Memory Integration

# Store successful patterns
npx @claude-flow/cli memory store --namespace browser-patterns --key "login-flow" --value "snapshot->fill->click->wait"

# Retrieve before similar task
npx @claude-flow/cli memory search --query "login automation"

Hooks

# Pre-browse hook (get context)
npx @claude-flow/cli hooks pre-edit --file "browser-task.ts"

# Post-browse hook (record success)
npx @claude-flow/cli hooks post-task --task-id "browse-1" --success true

Tips

Always use snapshots - They're optimized for AI with refs
Prefer -i flag - Gets only interactive elements, smaller output
Use refs, not selectors - More reliable, deterministic
Re-snapshot after navigation - Page state changes
Use sessions for parallel work - Each session is isolated

Before you install

Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
Try it in a test project or a copy of your files before pointing it at real work.
Pin the version you tested, and review changes before updating.
Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Browser?

Browser is a skill for Claude Code and Claude Cowork from the spencermarx/open-code-review repository on GitHub. Web browser automation with AI-optimized snapshots for claude-flow agents

How do I install Browser in Claude Code?

Download the browser folder from the repository. Save it as ~/.claude/skills/<skill-name>/SKILL.md for all projects, or .claude/skills/<skill-name>/SKILL.md for one project. Claude loads it automatically when a task matches; you can also run it with / and its name.

Can I use Browser in Claude Cowork?

Zip the skill folder so SKILL.md sits at the top level of the folder. Open Customize → Skills, click +, then upload the ZIP. Start a task that matches the description, or call it by name with /.

Is Browser safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under Apache-2.0. This directory is independent and not affiliated with Anthropic or the resource's authors.