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/tor-mcp/claude-mdgit clone --depth 1 https://github.com/globalion/tor-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/tor-mcp/claude-md)<a href="https://agentmods.dev/instructions/globalion/tor-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/globalion/tor-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 5.1 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
tor-mcp CLAUDE.md 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 5d 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 https://tor.regiq.in/api/admin/health Copies of this mod
1 near-identical copy found in the catalogue:
- tor-mcp CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploying tor-mcp to Hetzner + regiq.in
Server (shared with the rest of the Globalion MCP fleet)
- SSH:
[email protected] - Service directory:
/opt/tor-mcp/ - Domain:
tor.regiq.in(Cloudflare-tunnelled totor-mcp-web:3000) - Container names:
tor-mcp-tor,tor-mcp-web,tor-mcp-db - NEVER touch other people's folders under
/opt/— seeshreyas-onboarding.md§7.
Deploy
tar --exclude=node_modules --exclude=.next --exclude=.git -cf - . \
| ssh [email protected] "mkdir -p /opt/tor-mcp && tar -xf - -C /opt/tor-mcp/"
ssh [email protected] "cd /opt/tor-mcp && docker compose up -d --build"
First-time subdomain wiring
- Add to
/opt/platform/cloudflared/config.ymlon the server, BEFORE the catch-all:- hostname: tor.regiq.in service: http://tor-mcp-web:3000 - Restart tunnel:
ssh [email protected] "docker restart platform-cloudflared-1" - Create DNS:
ssh [email protected] "docker exec platform-cloudflared-1 cloudflared tunnel route dns 0caf1caf-59f6-4f36-9ea5-4aa9a9f41d0b tor.regiq.in"
Env vars
GOOGLE_CLIENT_ID/GOOGLE_CLIENT_SECRET— new OAuth client per subdomainNEXTAUTH_SECRET—openssl rand -base64 32NEXTAUTH_URL=https://tor.regiq.in,PUBLIC_BASE_URL=https://tor.regiq.inTOR_CONTROL_PASSWORD—openssl rand -hex 24. Web container uses it to send SIGNAL NEWNYM. Never exposed externally.[email protected]
Health
curl https://tor.regiq.in/api/admin/health
# expected: { ok: true, db: "ok", tor: { ok: true, ip: "185.220.101.42", country: "Netherlands" } }
Rules
- Never log request/response bodies. Only host + method + status + duration + size. Users route through Tor for privacy — logging kills the value.
- DNS through Tor. Always
socks5h://(notsocks5://). Thehsends hostname to Tor for resolution. - Control port never exposed to the internet. Only the internal docker network.
- Tor daemon takes 10-30s to bootstrap after container start — expect first requests to fail with
tor daemon unreachable. - Expose
/api/admin/health— the check hits check.torproject.org through Tor to verify actual routing.
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.
- 5d ago First seen · 50 lines · 674 tokens per session scan A c2514db9d213
tor-mcp CLAUDE.md is an instructions file published in the GitHub repository globalion/tor-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
timoni AGENTS.md
AGENTS.md instructions for stefanprodan/timoni, covering agents.md, what timoni is, common commands, architecture and cmd/timoni/ — cli (cobra).
selfhost-ai CLAUDE.md
Claude Code instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.
aks-mcp copilot-instructions.md
Copilot instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
gpt-rag-mcp deployment.instructions.md
Instructions for Azure/gpt-rag-mcp, a project described as: gpt-rag-mcp.
serverless-litellm CLAUDE.md
Instructions for cncoder/serverless-litellm, covering claude.md — litellm on eks 项目指南, 项目概述, 快速部署（一键）, 前置条件 and 部署流程.
openclaw-kubernetes AGENTS.md
Instructions for feiskyer/openclaw-kubernetes, covering agents.md, links, development commands, lint the chart against all values files and render templates to verify correctness (output discarded).