Overview
agent-browser is an open-source workflow skill for Claude Code and compatible agents, published by shanraisshan. Its author describes it as: “Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automatin…”. The project has 66k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/shanraisshan/claude-code-best-practice ~/.claude/skills/agent-browser`.
What agent-browser does
Every browser automation follows this pattern:
Best for
What’s inside
The SKILL.md for agent-browser is organised into these sections:
- Core Workflow
- Essential Commands
- Common Patterns
- Form Submission
- Authentication with State Persistence
- Data Extraction
- Parallel Sessions
- Visual Browser (Debugging)
- Local Files (PDFs, HTML)
- iOS Simulator (Mobile Safari)
- Ref Lifecycle (Important)
- Semantic Locators (Alternative to Refs)
Installation
Add agent-browser to your agent with:
git clone https://github.com/shanraisshan/claude-code-best-practice ~/.claude/skills/agent-browserReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
License
agent-browser is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in shanraisshan/claude-code-best-practice, an established project with 66,161 GitHub stars
- Works with Claude Code
- Actively maintained — repository updated in the last 30 days
- Its repository gained 2,365 GitHub stars over the last 52 days
Author
Topics
Alternatives to agent-browser
Similar skills from other repositories:
Compare agent-browser alternatives side by side →
Frequently asked questions
- What does agent-browser do?
- Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
- How do I install agent-browser?
- Run git clone https://github.com/shanraisshan/claude-code-best-practice ~/.claude/skills/agent-browser in your agent, then reload your skills. Review the source at https://github.com/shanraisshan/claude-code-best-practice before installing.
- Is agent-browser free to use?
- Yes. agent-browser is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does agent-browser work with?
- agent-browser lists Claude Code — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does agent-browser come from?
- agent-browser ships inside shanraisshan/claude-code-best-practice, a repository that contains 10 catalogued skills in total. The repository's 66,161 GitHub stars apply to that whole collection, not to this skill on its own.