maxwell2732/claudecode-research-harness-workflow/agent-browser

Claude Code and agent skill by maxwell2732/claudecode-research-harness-workflow

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Browser automation through the repo agent-browser CLI. Explicit helper for navigation, forms, screenshots, scraping, and web-app checks. Prefer Browser Use or Playwright when available. Do NOT load for: sharing URLs, embedding links, or editing screenshot files.

Install

npx vskill@latest install maxwell2732/claudecode-research-harness-workflow/agent-browser

SKILL.md

Agent Browser Skill

A skill for browser automation. Uses the agent-browser CLI to perform UI debugging, verification, and automated interaction.


Trigger Phrases

This skill is automatically invoked by the following phrases:

  • "Open this page", "Check the URL"
  • "Click on", "Type into", "Fill the form"
  • "Take a screenshot"
  • "Check the UI", "Test the screen"
  • "open this page", "click on", "fill the form", "screenshot"

Features

FeatureDetails
Browser AutomationSee references/browser-automation.md
AI Snapshot WorkflowSee references/ai-snapshot-workflow.md

Execution Steps

Step 0: Verify agent-browser
bash
# Check installation
which agent-browser
# If not installed
npm install -g agent-browser
agent-browser install
Step 1: Classify the User's Request
Request TypeAction
Open a URLagent-browser open <url>
Click an elementSnapshot → agent-browser click @ref
Fill a formSnapshot → agent-browser fill @ref "text"
Check stateagent-browser snapshot -i -c
Take screenshotagent-browser screenshot <path>
Debugagent-browser --headed open <url>
Step 2: AI Snapshot Workflow (Recommended)

For most operations, first take a snapshot and then interact using element references:

bash
# 1. Open the page
agent-browser open https://example.com
# 2. Take a snapshot (AI-optimized, interactive elements only)
agent-browser snapshot -i -c
# Sample output:
# - link "Home" [ref=e1]
# - button "Login" [ref=e2]
# - input "Email" [ref=e3]
# - input "Password" [ref=e4]
# - button "Submit" [ref=e5]
# 3. Interact via element references
agent-browser click @e2 # Click Login button
agent-browser fill @e3 "user@example.com"
agent-browser fill @e4 "password123"
agent-browser click @e5 # Submit
Step 3: Verify the Result
bash
# Check current state via snapshot
agent-browser snapshot -i -c
# Or check the URL
agent-browser get url
# Take a screenshot
agent-browser screenshot result.png

Quick Reference

Basic Operations
CommandDescription
open <url>Open a URL
snapshot -i -cAI-optimized snapshot
click @e1Click an element
fill @e1 "text"Fill a form
type @e1 "text"Type text
press EnterPress a key
screenshot [path]Take a screenshot
closeClose the browser
Navigation
CommandDescription
backGo back
forwardGo forward
reloadReload
Retrieving Information
CommandDescription
get text @e1Get text
get html @e1Get HTML
get urlCurrent URL
get titlePage title
Waiting
CommandDescription
wait @e1Wait for element
wait 1000Wait 1 second
Debugging
CommandDescription
--headedShow browser
consoleConsole logs
errorsPage errors
highlight @e1Highlight element

Session Management

Manage multiple tabs/sessions in parallel:

bash
# Specify a session
agent-browser --session admin open https://admin.example.com
agent-browser --session user open https://example.com
# List sessions
agent-browser session list
# Operate in a specific session
agent-browser --session admin snapshot -i -c

Choosing Between agent-browser and MCP Browser Tools

ToolRecommendationUse Case
agent-browser★★★First choice. Powerful AI-optimized snapshots
chrome-devtools MCP★★☆When Chrome is already open
playwright MCP★★☆Complex E2E testing

Principle: Try agent-browser first; use MCP tools only if it doesn't work.


Notes

  • agent-browser runs in headless mode by default
  • Use --headed to show the browser
  • Sessions persist until explicitly closed
  • Use sessions for sites requiring authentication

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/maxwell2732/claudecode-research-harness-workflow/agent-browser/badge)](https://verified-skill.com/skills/maxwell2732/claudecode-research-harness-workflow/agent-browser)

Something wrong with this skill or its page? Tell us.