vpn-setup: Skill for Claude Code

.claude/skills/vpn-security-check/SKILL.md

vpn-security-check is a skill for Claude Code from Sergei-thinker/vpn-setup. It costs 43 tokens per session (1,707 once invoked), scanned A, original, MIT.

A security-audit procedure for checking whether a VPN server is properly hardened. A VPN is a service that provides an encrypted connection to a private network.

In plain words
What is it for?
Use it to check SSH settings, firewall-related protections, and other listed VPN security controls after deployment or during periodic reviews.
Why use it?
It replaces assumptions about server security with command-based checks and recorded evidence for each result.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is Sergei-thinker/vpn-setup's own configuration. It tells Claude Code how to work on vpn-setup itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vpn-setup configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sergei-thinker/vpn-setup. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Sergei-thinker/vpn-setup/master/.claude/skills/vpn-security-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Sergei-thinker/vpn-setup

Made for: Claude Code.

Wrote 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.

agentmods badge for vpn-security-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergei-thinker/vpn-setup/vpn-security-check/github.svg)](https://agentmods.dev/skills/sergei-thinker/vpn-setup/vpn-security-check)
Your own site
<a href="https://agentmods.dev/skills/sergei-thinker/vpn-setup/vpn-security-check"><img src="https://agentmods.dev/badge/skills/sergei-thinker/vpn-setup/vpn-security-check/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.

agentmods 80×15 button for vpn-security-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergei-thinker/vpn-setup/vpn-security-check"><img src="https://agentmods.dev/badge/skills/sergei-thinker/vpn-setup/vpn-security-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01707
Opus 5 $0.00022 $0.00853
Sonnet 5 $0.00009 $0.00341
Haiku 4.5 $0.00004 $0.00171

Measured 9d ago against content hash 086b39429da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vpn-security-check scanned grade A with 2 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 9d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| World-readable (644, 755, etc.) | WARN — `python ssh_exec.py exec "chmod 600 /root/vpn-credentials.txt"` |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Command: `python ssh_exec.py exec "curl -s -o /dev/null -w '%{http_code}' http://localhost:80"`
.claude/skills/vpn-security-check/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VPN Infrastructure Security Audit

Checks that the VPN server is properly hardened. All checks run via ssh_exec.py — no additional tools needed.

When to Use

  • User asks about security: "check security", "is my VPN safe"
  • After initial deployment (offer proactively)
  • User has security concerns
  • Periodic security checkup

The Iron Law

EVERY CHECK MUST RUN A COMMAND. NO ASSUMPTIONS.

"quick-rebuild.sh enables the firewall" is not evidence that the firewall is active. Run the check.

Security Checks

Run ALL checks in order. Report each as PASS/FAIL/WARN with evidence.

1. SSH Hardening

1a. SSH Port

Command: python ssh_exec.py exec "grep -E '^Port ' /etc/ssh/sshd_config"

Result Rating
Port != 22 (e.g., 49152) PASS
Port 22 FAIL — TSPU scans and blocks port 22 to foreign IPs. Change with: python ssh_exec.py exec "sed -i 's/^Port 22/Port 49152/' /etc/ssh/sshd_config && systemctl restart sshd"

1b. Root Password Login

Command: python ssh_exec.py exec "grep -E '^PasswordAuthentication' /etc/ssh/sshd_config"

Result Rating
PasswordAuthentication no PASS
PasswordAuthentication yes WARN — Key-only auth is more secure. Note: some beginners use password auth intentionally. Inform, don't force change
Not set (commented out) WARN — defaults to yes on most distros

2. Firewall

2a. UFW Status

Command: python ssh_exec.py exec "ufw status verbose"

Result Rating
Status: active, rules for 443/8443/2053/SSH port PASS
Status: inactive FAIL — python ssh_exec.py exec "ufw --force enable"
Active but missing expected ports WARN — check if needed ports are open

2b. Open Ports (reality check)

Command: python ssh_exec.py exec "ss -tnlp | grep -E 'LISTEN' | awk '{print \$4, \$6}'"

Verify only expected services are listening:

  • xray on 443, 8443, 2053 (VPN)
  • x-ui panel (some high port)
  • sshd on configured port
  • nginx on 80 (camouflage)

Read the full file on GitHub · 196 lines

Changes

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.

  1. 9d ago First seen · 196 lines · 43 tokens per session scan A 086b39429da0

Subscribe to this mod's changes

vpn-security-check is a skill published in the GitHub repository Sergei-thinker/vpn-setup (184 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,707 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

Xrayebator: your own VPN on a VPS (Xray Reality)

Use when the user needs their own VPN/proxy on a VPS to bypass regional blocks or DPI so research APIs and browsers work through a clean exit. One-script Xray VLESS+REALITY installer and client manager.

howdeploy/deploychan_mcp · 60 tokens

identity-work

A guided reflection skill for recognising when personal labels or fixed positions are distorting judgement, then using a new self-image to support behaviour change.

kangarooking/cangjie-skill · 126 tokens

mpstats-connector

A connector for MPStats, a paid analytics service for Ozon and Wildberries marketplace products. It reports sales, prices, stock, warehouses, and seller or brand details for specific items.

Vladimir-Human/ru-marketplace-mcp · 126 tokens

citilink-connector

A connector for searching Citilink and reading individual electronics product cards. Citilink is an electronics retailer, and the connector reads its rendered pages through an operator-controlled Chrome browser.

Vladimir-Human/ru-marketplace-mcp · 75 tokens

compare-prices

Use this skill when the operator asks where something is cheapest across marketplaces. Fans out to ten searchable sources — Wildberries, Ozon, Yandex Market, Avito, Taobao, Megamarket, Lamoda, DNS, Citilink and AliExpress (Detsky Mir is excluded — no text search; Taobao is ranked in yuan, never against rubles).…

Vladimir-Human/ru-marketplace-mcp · 132 tokens

aliexpress-connector

Use this skill when the operator asks to search AliExpress or read one of its product cards. Two tools, aliexpresssearch and aliexpresscard; prices in rubles; rating and order counts included, review TEXTS intentionally not exposed. CDP-only: without the scraping-profile Chrome this source answers nothing. Trigger on…

Vladimir-Human/ru-marketplace-mcp · 0 tokens