mcp-browser-bridge: Command for Claude Code

.claude/commands/browse.md

browse is a command for Claude Code from adbarc92/mcp-browser-bridge. It costs 0 tokens per session (449 once invoked), scanned A, original, MIT.

A set of commands for controlling a web browser through MCP Browser Bridge tools.

In plain words
What is it for?
Use it to open pages, view screenshots, read page content, run page JavaScript, fill forms, click elements, inspect tabs, and check console logs.
Why use it?
It lets an agent inspect and operate web pages instead of working only with local code or text.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is adbarc92/mcp-browser-bridge's own configuration. It tells Claude Code how to work on mcp-browser-bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-browser-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adbarc92/mcp-browser-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adbarc92/mcp-browser-bridge/master/.claude/commands/browse.md
Clone the repo
git clone --depth 1 https://github.com/adbarc92/mcp-browser-bridge

Made for: Claude Code.

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.

agentmods badge for browse

README.md
[![agentmods](https://agentmods.dev/badge/commands/adbarc92/mcp-browser-bridge/browse.svg)](https://agentmods.dev/commands/adbarc92/mcp-browser-bridge/browse)
Your own site
<a href="https://agentmods.dev/commands/adbarc92/mcp-browser-bridge/browse"><img src="https://agentmods.dev/badge/commands/adbarc92/mcp-browser-bridge/browse.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00000 $0.00449
Opus 5 $0.00000 $0.00225
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured 6d ago against content hash 15a81e572463, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

browse 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 6d 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.

.claude/commands/browse.md · 39 lines

What it actually says

You have access to a browser via the MCP Browser Bridge tools. Use them to interact with web pages.

Available Tools

Tool Purpose
browser_status Check connection and get active tab info
browser_navigate Go to a URL
browser_screenshot Capture visible area of a tab
browser_evaluate Run JavaScript in the page context
browser_click Click an element by CSS selector
browser_fill Fill a form field by CSS selector
browser_get_content Get text or HTML of a page or element
browser_get_tabs List all open tabs
browser_get_console Get console logs from a tab
browser_wait_for Wait for a selector to appear

Workflow

  1. Always start with browser_status to confirm the extension is connected.
  2. Use browser_navigate to go to the target page.
  3. Use browser_screenshot to see the current state before interacting.
  4. After any interaction (click, fill), take another screenshot to verify the result.

Selector Tips

  • Prefer [data-testid="foo"] selectors when available (React/RN Web projects use these).
  • Use button:has-text("Submit") is NOT supported — use browser_evaluate to find elements by text content instead.
  • For scrolling, use browser_evaluate with document.querySelector('selector').scrollIntoView(). Do NOT use window.scrollBy() — it doesn't work with framework scroll containers.

Gotchas

  • Screenshots require a visible, focused tab. Minimized or background tabs will fail.
  • browser_evaluate results must be JSON-serializable. Promises return {} — use synchronous expressions or await inside an IIFE and return a primitive/plain object.
  • browser_fill works with React. It uses native property setters to trigger React state updates.
  • All tools accept an optional tabId. Omit it to target the active tab.

Task: $ARGUMENTS

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. 6d ago First seen · 39 lines · 0 tokens per session scan A 15a81e572463

Subscribe to this mod's changes

browse is a command published in the GitHub repository adbarc92/mcp-browser-bridge (1 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 449 tokens. 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 2026-08-31.