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.
npx agentmods add instructions/globalion/browser-mcp/claude-mdgit clone --depth 1 https://github.com/globalion/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/instructions/globalion/browser-mcp/claude-md)<a href="https://agentmods.dev/instructions/globalion/browser-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/globalion/browser-mcp/claude-md.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 | $0.00523 | $0.00523 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
browser-mcp CLAUDE.md 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 4d 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.
This is a copy
100% identical to browser-mcp CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Deploying browser-mcp to Hetzner + regiq.in
Server
- SSH:
[email protected] - Service dir:
/opt/browser-mcp/ - Domain:
browser.regiq.in - Containers:
browser-mcp-web,browser-mcp-db - NEVER touch other people's folders under
/opt/.
Deploy
tar --exclude=node_modules --exclude=.next --exclude=.git -cf - . \
| ssh [email protected] "mkdir -p /opt/browser-mcp && tar -xf - -C /opt/browser-mcp/"
ssh [email protected] "cd /opt/browser-mcp && docker compose up -d --build"
The Playwright base image is ~2 GB — first build takes 5-10 min.
Subdomain wiring
/opt/platform/cloudflared/config.yml, before the catch-all:
- hostname: browser.regiq.in
service: http://172.17.0.1:3013
Then:
ssh [email protected] "docker restart platform-cloudflared-1"
ssh [email protected] "docker exec platform-cloudflared-1 cloudflared tunnel route dns 0caf1caf-59f6-4f36-9ea5-4aa9a9f41d0b browser.regiq.in"
Env vars
NEXTAUTH_SECRET,NEXTAUTH_URL=https://browser.regiq.in,PUBLIC_BASE_URL=https://browser.regiq.inGOOGLE_CLIENT_ID/GOOGLE_CLIENT_SECRET— Google Cloud OAuthGITHUB_CLIENT_ID/GITHUB_CLIENT_SECRET— GitHub OAuth AppCRED_ENCRYPTION_KEY—openssl rand -hex 32— REQUIRED. Rotating invalidates every saved credential.ADMIN_EMAILS— comma-separated, defaults to [email protected]
Rules
- No LLM in this stack. Users bring their own agent.
- Sessions live in memory. A container restart kills all active browser sessions — users have to
browser_new_sessionagain. - Credentials encrypted at rest. Never returned raw over the API — only typed into forms server-side via
use_credentials. - Expose
/api/admin/health.
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.
- 4d ago First seen · 48 lines · 523 tokens per session scan A c3bef92fcc0d
browser-mcp CLAUDE.md is an instructions file published in the GitHub repository globalion/browser-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to browser-mcp CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.
shantycrawl-mcp AGENTS.md
AGENTS.md instructions for schlemperdev/shantycrawl-mcp, covering shantycrawl mcp -- dynamic firecrawl mcp server, purpose, ownership, local contracts and work guidance.
AIPex CLAUDE.md
Instructions for AIPexStudio/AIPex, a project described as: AIPex: AI browser automation assistant, no migration and privacy first. Alternative to Manus Browser Operator、 Claude Chrome and Agent Browser.