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.
curl -O https://raw.githubusercontent.com/adbarc92/mcp-browser-bridge/master/.claude/commands/browse.mdgit clone --depth 1 https://github.com/adbarc92/mcp-browser-bridgeWrote 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.
[](https://agentmods.dev/commands/adbarc92/mcp-browser-bridge/browse)<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>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 | $0.00000 | $0.00449 |
| Opus 5 | $0.00000 | $0.00225 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
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.
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
- Always start with
browser_statusto confirm the extension is connected. - Use
browser_navigateto go to the target page. - Use
browser_screenshotto see the current state before interacting. - 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 — usebrowser_evaluateto find elements by text content instead. - For scrolling, use
browser_evaluatewithdocument.querySelector('selector').scrollIntoView(). Do NOT usewindow.scrollBy()— it doesn't work with framework scroll containers.
Gotchas
- Screenshots require a visible, focused tab. Minimized or background tabs will fail.
browser_evaluateresults must be JSON-serializable. Promises return{}— use synchronous expressions or await inside an IIFE and return a primitive/plain object.browser_fillworks 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
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.
- 6d ago First seen · 39 lines · 0 tokens per session scan A 15a81e572463
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.
Other commands, from other repositories
qa
Dispatch a verifiable browser task to the qa-tester subagent. Use for regression checks, smoke tests, and any task with a clean pass/fail outcome. Supports an EXHAUSTIVE mode that verifies every control behind an honesty gate.
playbook
Manage Mochi playbooks (list, show, run, delete). Plays through the browser MCP tools.
unschedule-playbook
Cancel a scheduled playbook routine.
computer
Control the macOS desktop — move mouse, click, type, press keys, scroll, drag, take screenshots, list windows/displays, clipboard. Uses usecomputer CLI for native Quartz event automation.
check-browser
Use Real Browser MCP to check what's currently showing in my browser.
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.