A skill for directly controlling a web browser, including opening pages, clicking controls, entering text, scrolling, and inspecting what is shown. It provides step-by-step control over browser actions.

Use it to navigate websites, fill in forms, search the web, switch tabs, wait for page conditions, inspect elements, and take screenshots.

It helps when an automated browser task needs precise actions or checks at each stage. It can also be used when higher-level browser automation gets stuck.

browser — 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

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

Your own site

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

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,189 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	$0.00033	$0.01189
Opus 5	$0.00016	$0.00594
Sonnet 5	$0.00007	$0.00238
Haiku 4.5	$0.00003	$0.00119

Measured 9d ago against content hash 9d7ed39e946e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

browser 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 9d 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/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser - Direct Browser Control

Overview

Direct control of browser interactions. Use for simple, single actions.

When to Use

browser provides low-level, precise control over browser operations:

When you need explicit control over each action
When you want to verify results at each step
As a fallback when browser-use agent fails or gets stuck
Any browser automation task (navigation, clicking, form filling, etc.)

Note: browser and browser-use are complementary. Both can accomplish the same tasks - browser gives precise step-by-step control, while browser-use provides high-level task automation.

Available Actions

Action	Description
`get_browser_state`	Get current browser state including tabs, DOM content, and highlighted screenshot
`browser.get_element_info`	Get element details by index (xpath, position, attributes, visibility)
`browser.search`	Google search
`browser.navigate`	Navigate to URL
`browser.go_back`	Go back
`browser.wait`	Wait for condition
`browser.click`	Click element
`browser.input`	Input text into field
`browser.switch`	Switch to another tab by tab_id
`browser.close`	Close a tab by tab_id
`browser.extract`	LLM extracts structured data from page markdown
`browser.scroll`	Scroll page
`browser.send_keys`	Send keyboard keys
`browser.find_text`	Scroll to and find text
`browser.dropdown_options`	Get dropdown options
`browser.select_dropdown`	Select dropdown option
`browser.evaluate`	Execute JavaScript in browser
`browser.hover`	Hover on element
`browser.download_media`	Download media from URL
`browser.get_html_content`	Get HTML content and save to file
`browser.reload_page`	Refresh current page
`browser.start_console_logging`	Start monitoring console logs (console.log/warn/error)
`browser.stop_console_logging`	Stop console logging and retrieve all logs
`browser.start_network_logging`	Start monitoring network traffic (requests/responses)
`browser.stop_network_logging`	Stop network logging and get HAR file

Read the full file on GitHub · 131 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.

9d ago First seen · 131 lines · 33 tokens per session scan A 9d7ed39e946e

Subscribe to this mod's changes

browser is a skill published in the GitHub repository vibesurf-ai/claude-surf (24 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 1,189 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