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/sergei-thinker/vpn-setup/claude-mdgit clone --depth 1 https://github.com/Sergei-thinker/vpn-setupWrote 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/sergei-thinker/vpn-setup/claude-md)<a href="https://agentmods.dev/instructions/sergei-thinker/vpn-setup/claude-md"><img src="https://agentmods.dev/badge/instructions/sergei-thinker/vpn-setup/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 | $0.02498 | $0.02498 |
| Opus 5 | $0.01249 | $0.01249 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
vpn-setup 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 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VPN Infrastructure -- Инструкции для Claude Code
Как работать с пользователем
Пользователь может прийти по-разному:
- Клонировал репозиторий и просит "разверни VPN" -- перейти к деплою (проверить .env)
- Скинул ссылку на этот репо и просит развернуть VPN -- объяснить что нужно:
- Арендовать VPS (~$2-5/мес): любой EU-провайдер вне РФ (Нидерланды/Швеция/Финляндия/Германия, Debian 12). НЕ российские хостинги (Aeza, VDSina, REG.RU — подчиняются РКН). НЕ крупные облака (Hetzner/OVH/DigitalOcean — IP-диапазоны блокируются ТСПУ)
- Установить VPN-клиент: v2rayN (Windows, бесплатно), Shadowrocket (iOS, $2.99), v2rayNG (Android, бесплатно)
- Дать IP-адрес VPS и SSH-доступ
- Затем: клонировать репо, заполнить .env, запустить деплой
- Спрашивает что это -- объяснить кратко и предложить помочь с установкой
Общайся с пользователем на русском языке.
Описание проекта
Многоуровневая VPN-инфраструктура на базе VLESS Reality для обхода ТСПУ/DPI блокировок в России.
- Протокол: VLESS + XTLS Reality (трафик неотличим от HTTPS к microsoft.com/google.com/apple.com)
- Панель управления: 3X-UI + Xray-core
- Клиенты: v2rayN (Windows, рекомендуемый), Hiddify (альтернатива), Shadowrocket (iOS), v2rayNG (Android)
- Подробное руководство для ручной настройки: GUIDE.md
Архитектура
Каждый следующий уровень активируется когда предыдущий заблокирован.
| Layer | Метод | Роль | Статус |
|---|---|---|---|
| 0 | VLESS Reality (прямое, порты 443/8443/2053) | Основной | Работает |
| 1 | Relay через российский VPS (xHTTP, SNI: gosuslugi.ru) | Главный fallback -- обход белых списков на мобильных | Работает |
| 2 | WebRTC через Яндекс.Телемост (OlcRTC) | Аварийный (пока только десктоп -- мобильное приложение OlcRTC ещё не создано) | Скрипты готовы |
| 3 | Cloudflare CDN (WebSocket через домен пользователя) | Backup для Wi-Fi (Cloudflare блокируется ТСПУ с 2025) | Работает только на Wi-Fi |
Split routing: Российские сайты (Yandex, VK, Госуслуги, банки) идут напрямую, минуя VPN.
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 · 187 lines · 2,498 tokens per session scan A 7013602c6427
vpn-setup CLAUDE.md is an instructions file published in the GitHub repository Sergei-thinker/vpn-setup (180 stars, last pushed 4mo ago), licensed MIT. It adds 2,498 tokens to every session, about $0.0125 per session on Opus 5. 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 instructions, from other repositories
setup-3xui-skill GEMINI.md
Gemini CLI instructions for betzaydarobie-source/setup-3xui-skill, a project described as: Reusable setup-3xui AI-agent workflow for installing 3X-UI panels and managing VLESS Reality clients.
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.