An autonomous browser agent that carries out multi-step web tasks from a described goal, even when the website or process is unfamiliar.

Use it to navigate websites, fill in forms, extract structured data, and run browser tasks across one or more tabs.

It removes the need to specify every click and lets the agent discover pages, interact with controls, and complete longer browser procedures.

browser-use — Skill for Claude Code by vibesurf-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add vibesurf-ai/claude-surf --skill browser-use

Clone the repo

git clone --depth 1 https://github.com/vibesurf-ai/claude-surf

Made for: Claude Code.

Or install surf, the plugin that ships this one along with the rest of its 21 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/browser-use/github.svg)](https://agentmods.dev/skills/vibesurf-ai/claude-surf/browser-use)

Your own site

<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/browser-use"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/browser-use/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vibesurf-ai/claude-surf/browser-use"><img src="https://agentmods.dev/badge/skills/vibesurf-ai/claude-surf/browser-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 954 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00954
Opus 5	$0.00017	$0.00477
Sonnet 5	$0.00007	$0.00191
Haiku 4.5	$0.00003	$0.00095

Measured 10d ago against content hash 2da2320af634, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

browser-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/browser-use/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser-Use Agent - Autonomous Automation

Overview

Launch AI sub-agents that complete multi-step browser tasks autonomously. Most powerful VibeSurf capability.

When to Use

browser-use is a high-level, task-oriented sub-agent approach:

Complex tasks where you describe the goal and desired output, let the agent figure out the steps
Long workflows that would require many manual browser operations
Unknown or dynamic UI that needs autonomous exploration
Parallel automation across multiple tabs

Note: browser-use and browser skill are complementary, not mutually exclusive. Both can accomplish the same tasks - browser-use is higher-level automation, while browser gives you precise control.

Available Actions

Action	Description
`execute_browser_use_agent`	Execute browser-use agent tasks. Specify tab_id to work on specific tab. Each tab_id must be unique during parallel execution.

How It Works

Describe the goal, agent figures out the steps:

Navigate to URLs
Find and interact with elements
Fill forms
Extract data
Return structured results

Task-Oriented Thinking

Good task descriptions:

✅ "Fill out the registration form with these details"
✅ "Search for Python tutorials and summarize top 3"
✅ "Go to login page, authenticate, then check dashboard"

Bad task descriptions:

❌ "Click button" (too vague, use browser)
❌ "Extract prices" (use js_code instead)
❌ "Step 1: navigate, Step 2: click..." (let agent figure it out)

Working with Existing Tabs

🎯 Important: tab_id Selection

When user refers to their already-opened pages (e.g., "the current page", "from my open tabs", "the second tab"):

FIRST call get_browser_state to get all open tabs and their IDs

THEN use the correct tab_id from the response

NEVER use tab_id: null or omit it - that creates a NEW tab

Key distinction:

tab_id: "existing_id" → Work on user's existing tab

tab_id: null or omitted → Create a brand new tab

Read the full file on GitHub · 108 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 108 lines · 35 tokens per session scan A 2da2320af634

Subscribe to this mod's changes

browser-use is a skill published in the GitHub repository vibesurf-ai/claude-surf (24 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 954 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation Claude Code claude-plugin vibe-coding vibesurf

moai-platform-chrome-extension

Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome. APIs, side panel, declarativeNetRequest, and Chrome Web Store publishing. Use when building browser extensions.

modu-ai/moai-adk · 48 tokens

memstack-development-webapp-testing

Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.

cwinvestments/memstack · 75 tokens

browser-use