Agent Browser

Agent Browser is an Automation skill for Claude Code, published by withkynam in vibecode-pro-max-kit.

1.1K stars227 forkson withkynam/vibecode-pro-max-kitAdded 2026/08/20+1% in starsRepository updated 2026/06/21

agenticai-agentsai-coding-assistantai-developmentai-workflowanthropicclaudeclaude-codecli-toolscode-qualitycodexcoding-agentscursordeveloper-toolsllmopenaiprompt-engineeringtypescriptvibe-codingvibecoding

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/withkynam/vibecode-pro-max-kit/tree/main/.claude/skills/vc-agent-browser ~/.claude/skills/vc-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/withkynam/vibecode-pro-max-kit.git

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

In this catalog

Source file: .claude/skills/vc-agent-browser/SKILL.md in withkynam/vibecode-pro-max-kit
Installs to: ~/.claude/skills/vc-agent-browser
Collection: One of 25 skills cataloged from this repository
Category: Automation — 1523 skills

What Agent Browser does

Agent Browser automates web interactions for AI agents using compact snapshots and refs. Use it for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing.

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

Documentation

README

Excerpt

agent-browser Skill

Browser automation CLI designed for AI agents. Uses "snapshot + refs" paradigm for 93% less context than Playwright MCP.

Quick Start

# Install globally
npm install -g agent-browser

# Download Chromium (one-time)
agent-browser install

# Linux: include system deps
agent-browser install --with-deps

# Verify
agent-browser --version

Core Workflow

The 4-step pattern for all browser automation:

# 1. Navigate
agent-browser open https://example.com

# 2. Snapshot (get interactive elements with refs)
agent-browser snapshot -i
# Output: button "Sign In" @e1, textbox "Email" @e2, ...

# 3. Interact using refs
agent-browser fill @e2 "user@example.com"
agent-browser click @e1

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

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

Frequently asked about Agent Browser

What else does withkynam publish alongside Agent Browser?
Agent Browser is one of 25 skills that DirSkills catalogs from withkynam/vibecode-pro-max-kit, the repository it ships in. Its siblings there include Agent Strategy Compare, Audit Context and Audit Plans. Each one is a separate skill with its own page in this directory, installs the same way Agent Browser does, and is maintained by withkynam in that same repository. The rest of the collection is listed on the withkynam/vibecode-pro-max-kit page.
How does Agent Browser compare to other Automation skills?
Agent Browser ranks #782 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.