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.
git clone --depth 1 https://github.com/ofershap/real-browser-mcpWrote 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/ofershap/real-browser-mcp/check-browser)<a href="https://agentmods.dev/commands/ofershap/real-browser-mcp/check-browser"><img src="https://agentmods.dev/badge/commands/ofershap/real-browser-mcp/check-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.
<a href="https://agentmods.dev/commands/ofershap/real-browser-mcp/check-browser"><img src="https://agentmods.dev/badge/commands/ofershap/real-browser-mcp/check-browser.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00197 |
| Opus 5.5 | $0.00000 | $0.00079 |
| Sonnet 5.5 | $0.00000 | $0.00039 |
| Haiku 4.5 | $0.00000 | $0.00020 |
Grade A, and why
check-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 1mo 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
check-browser
Use Real Browser MCP to check what's currently showing in my browser.
Steps
- Call
browser_snapshotto see the current page structure - Based on what you find, take a
browser_screenshotif visual verification is needed - Report back what you see - page title, key elements, any errors or unexpected state
- If I asked you to verify something specific, focus on that
When to use
- After making a code change, to verify it rendered correctly
- To check if a form works, a button does what it should, or content loaded
- To read page content I'm looking at
- To debug visual issues or check responsive layout
Important
- This is my REAL browser. I'm already logged in everywhere.
- Don't close tabs I didn't ask you to close
- Don't navigate away from the current page unless I ask you to
- Use element refs from snapshots for any interactions
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.
- 1mo ago First seen · 25 lines · 0 tokens per session scan A c830ac5ddbe8
check-browser is a command published in the GitHub repository ofershap/real-browser-mcp (56 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 197 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 2026-08-30.
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.
check-browser
Use Browser Controller to check what's currently showing in my browser.
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.
chrome
Check Chrome Actuator connection and remind how to install the native host.