Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Vps Guided Install

ASecurity

Use when installing a 24/7 AI agent on a bare-metal VPS without Docker, from SSH keys to hardening to Telegram to systemd persistence. Triggers on \"vps guided install\", \"hermes vps\", \"claude 24/7 vps\", \"bare-metal agent\", \"kvm1 vs kvm2\". Non-triggers: one-click managed host or Docker-based deploy (use cloud-code-vps-deploy). Outcome: a hardened Ubuntu 24.04 VPS with subscription-login brain, Telegram allowlist, systemd services, cron smoke test, backup and reboot persistence verified.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgodockerapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill vps-guided-install --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vps Guided Install?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Vps Guided Install
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-vps-guided-install/badge)](https://www.skillsdirectory.com/skills/majinmagros-vps-guided-install)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: vps-guided-install
description: "Use when installing a 24/7 AI agent on a bare-metal VPS without Docker, from SSH keys to hardening to Telegram to systemd persistence. Triggers on \"vps guided install\", \"hermes vps\", \"claude 24/7 vps\", \"bare-metal agent\", \"kvm1 vs kvm2\". Non-triggers: one-click managed host or Docker-based deploy (use cloud-code-vps-deploy). Outcome: a hardened Ubuntu 24.04 VPS with subscription-login brain, Telegram allowlist, systemd services, cron smoke test, backup and reboot persistence verified."
metadata:
  origin: ECC
---

# VPS Guided Install

Guided bare-metal install for 24/7 agents on a VPS, with no Docker and
no tmux. Covers one machine from empty Ubuntu to a hardened host that
survives reboot, notifies over Telegram, and runs agents as systemd
services. This is the operational companion to `cloud-code-vps-deploy`,
which covers only the generic one-click path in a few lines.

## When To Activate

- The user says VPS, KVM1, KVM2, Hermes on VPS, Claude 24/7, agent on
  phone, bare-metal install, or guided VPS playbook.
- The goal is an always-on agent that keeps running with the PC off,
  with crons inside the plan and remote control from mobile.
- A previous VPS attempt failed on SSH, hardening, Telegram wiring,
  reboot persistence, or secret migration.
- The user must choose between a small single-agent box and a larger
  multi-agent box before provisioning.

## Sizing Matrix

- **KVM1 4GB**: one Claude-style agent, remote control plus a few
  crons. Cheapest box that stays responsive. Pick this for a single
  brain with light scheduled work.
- **KVM2 8GB**: Hermes plus Claude side by side, or several crons with
  browser and scraping steps. Pick this for multi-agent or daily
  content plus traffic routines.
- Rule: start on the smaller box only for a single passive agent. Move
  to the larger box before adding a second active brain or heavy cron
  set. Box sizes and prices in videos are author measurements, not
  benchmarks - re-check the host catalog before buying.

## Workflow

### 1. Provision and SSH access

- Provision Ubuntu 24.04 LTS on the chosen box.
- Create a non-root ops user with sudo, disable root login.
- Generate an SSH key pair locally, copy the public key to the VPS,
  and add a short alias in the SSH config:

```text
Host vps-agent
  HostName <vps-ip>
  User <ops-user>
  IdentityFile <path-to-private-key>
```

- Verify `ssh vps-agent` works without a password prompt before
  continuing. No further step runs over password auth.

### 2. Harden the box

- Enable the firewall with default-deny inbound, allow only SSH plus
  explicitly required ports.
- Set SSH to key-only: disable password auth and challenge-response.
- Keep any agent dashboard on localhost only. Reach it through an SSH
  tunnel, never by exposing a public port:

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →