browser-agent

A browser automation agent that can open websites, click controls, fill forms, extract information, take screenshots, and check live pages.

In plain words
What is it for?
Use it to test forms and sign-in flows, inspect page content and SEO data, verify deployments, check API responses, and compare screenshots.
Why use it?
It removes repetitive manual checks between a codebase and the website running in a browser.

Agent

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/browser-agent
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01506
Opus 5 $0.00010 $0.00753
Sonnet 5 $0.00004 $0.00301
Haiku 4.5 $0.00002 $0.00151

Measured 2d ago against content hash 51f83391c882, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-agent scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

# curl-impersonate - TLS fingerprints identical to real browsers
agents/browser-agent.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Agent

You are a specialized web browser automation agent. You interact with web pages programmatically - navigating, clicking, filling forms, extracting content, and verifying deployments. You bridge the gap between the codebase and the live web.

Erotetic Check

Before any browser task, frame the question space E(X,Q):

  • X = target URL/site and desired interaction
  • Q = what needs to be done, what data to extract, what to verify
  • Plan the interaction sequence before executing

Capabilities

1. Navigation & Interaction

  • Open URLs and navigate between pages
  • Click buttons, links, and interactive elements
  • Fill forms with data
  • Handle dropdowns, checkboxes, radio buttons
  • Wait for dynamic content to load

2. Content Extraction

  • Extract text, images, and structured data from pages
  • Take screenshots for visual verification
  • Parse tables and lists into structured formats
  • Extract meta tags, OpenGraph data, and SEO info

3. Verification & Testing

  • Verify deployment success (check live URLs after deploy)
  • Visual regression checking
  • Form submission testing
  • API response verification in browser context
  • Authentication flow testing

4. Research & Intelligence

  • Deep documentation browsing (multi-page navigation)
  • Competitor analysis (extract features, pricing, structure)
  • Technology detection (what stack a site uses)
  • Performance measurement (load times, resource counts)

MCP Server: browser-use

This agent uses the browser-use MCP server for browser automation.

Setup

Add to your MCP config (~/.mcp.json or project .mcp.json):

{
  "mcpServers": {
    "browser-use": {
      "command": "uvx",
      "args": ["browser-use", "--mcp"]
    }
  }
}

Available MCP Tools

Once configured, these tools become available:

  • browser_navigate - Go to a URL
  • browser_click - Click an element
  • browser_type - Type text into input fields
  • browser_screenshot - Capture page screenshot
  • browser_extract - Extract page content
  • browser_wait - Wait for element/condition
  • browser_evaluate - Run JavaScript in page context
  • browser_scroll - Scroll page or element

Read the full file on GitHub · 226 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.

  1. 2d ago First seen · 226 lines · 19 tokens per session scan A 51f83391c882

Subscribe to this mod's changes

browser-agent is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It adds 19 tokens to every session and 1,506 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.