🌐
AutomationHTML

Agent Browser

by shanraisshan

Agent Browser is an Automation skill for Claude Code, published by shanraisshan in claude-code-best-practice.

64.4K stars6.4K forkson shanraisshan/claude-code-best-practiceAdded 2026/08/13Repository updated 2026/08/13
agentic-aiagentic-codingagentic-engineeringagentic-workflowaiai-agentsanthropicbest-practicesborisclaudeclaude-aiclaude-codeclaude-code-agentsclaude-code-best-practicesclaude-code-commandsclaude-code-skillscontext-engineeringpakistanpakistani-developervibe-coding
Install in seconds
Install Agent Browser
Copy Agent Browser into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/shanraisshan/claude-code-best-practice/tree/main/.claude/skills/agent-browser ~/.claude/skills/agent-browser

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/shanraisshan/claude-code-best-practice.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
.claude/skills/agent-browser/SKILL.md in shanraisshan/claude-code-best-practice
Installs to
~/.claude/skills/agent-browser
Collection
One of 10 skills cataloged from this repository
Category
Automation1523 skills

What Agent Browser does

Agent Browser is a command-line browser automation tool that lets AI agents navigate pages, fill forms, click buttons, take screenshots, extract data, and test web apps. Use it when asked to open websites, automate form submissions, or perform any programmatic web interaction.

Agent Browser is cataloged under Automation on DirSkills. Agent Browser comes from a repository tagged agentic-ai, agentic-coding, agentic-engineering, agentic-workflow and ai.

Documentation

README

Browser Automation with agent-browser

Core Workflow

Every browser automation follows this pattern:

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
  3. Interact: Use refs to click, fill, select
  4. Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Essential Commands

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Browser

  • What else does shanraisshan publish alongside Agent Browser?

    Agent Browser is one of 10 skills that DirSkills catalogs from shanraisshan/claude-code-best-practice, the repository it ships in. Its siblings there include Claude Code Extension Mechanisms, Pakistan Time and Presentation Structure. Each one is a separate skill with its own page in this directory, installs the same way Agent Browser does, and is maintained by shanraisshan in that same repository. The rest of the collection is listed on the shanraisshan/claude-code-best-practice page.

  • How does Agent Browser compare to other Automation skills?

    Agent Browser ranks #25 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Browser against them. Open each page to compare what they document and how they install.

More from shanraisshan/claude-code-best-practice

Agent Browser is one of 10 skills cataloged on DirSkills from shanraisshan/claude-code-best-practice.

See all 10 skills
🧩
3w ago

Claude Code Extension Mechanisms

Claude Code Extension Mechanisms compares subagents, commands, and skills in Claude Code to help you choose the right mechanism for autonomous tasks, user-triggered workflows, or reusable procedures.
AI Engineering
64.4K6.4K
🕒
3w ago

Pakistan Time

Pakistan Time displays the current date and time in Pakistan Standard Time (PKT, UTC+5). Use when the user asks for the current time, Pakistan time, or PKT.
Automation
64.4K6.4K
📽️
3w ago

Presentation Structure

Presentation Structure explains the slide format, journey bar level system, navigation, and section structure for the presentation at presentation/index.html. Use it when editing slides to keep numbering, level transitions, and navigation correct.
Frontend
64.4K6.4K
🎨
3w ago

Presentation Styling

Presentation Styling provides CSS classes, component patterns, and syntax highlighting for building slides in a presentation. Use it when styling slides, code blocks, journey bars, or weighted badges.
Frontend
64.4K6.4K
🕒
3w ago

Time Fetcher

Time Fetcher provides a bash command to fetch the current Dubai time in Asia/Dubai. Use it when you need the current time in Gulf Standard Time (UTC+4), including formatted and time-only fields.
Automation
64.4K6.4K
🕒
3w ago

Time SVG Creator

Time SVG Creator creates a visual SVG time card showing the current time for Dubai and writes it to agent-teams/output/dubai-time.svg. Use it when you need a self-contained SVG time card and markdown summary from provided time values.
Frontend
64.4K6.4K