Run any Skill in Manus with one click

vps-server-management

Stars44

Forks7

UpdatedJuly 7, 2026 at 11:47

Use when David wants to manage his VPS servers and the AI agents running inside them — connecting, deploying, monitoring, restarting, and operating remote hosts and their agents. Triggers on VPS, server management, remote host, SSH into server, manage my servers, agents on the server.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

adriannoes

adriannoes/awesome-vibe-coding

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Network and Computer Systems AdministratorsComputer and Mathematical Occupations·SOC 15-1244

SKILL.md

readonly

name	vps-server-management
description	Use when David wants to manage his VPS servers and the AI agents running inside them — connecting, deploying, monitoring, restarting, and operating remote hosts and their agents. Triggers on VPS, server management, remote host, SSH into server, manage my servers, agents on the server.

VPS Server Management

Source of truth: <path-to-infrastructure-doc>/infrastructure.md (read it for the latest — IPs/expirations change).

Servers (Hostinger VPS) — 3 total

Hostname	OS	Purpose
personal.openclaw	Ubuntu 24.04 (Dokploy)	OpenClaw — personal instance
n8n.automations	Ubuntu 24.04 (n8n)	All n8n workflow automations (primary)
private.hermes	Ubuntu 24.04	Hermes Agent — Discord gateway

SSH as root@<IP>.

Access levels (never share higher than needed)

App login — e.g. <n8n-app-hostname>. Build/edit workflows, no server access. Safest to share.
VPS SSH — root@<IP>. Docker, files, system config. Trusted technical people only.
Hostinger hPanel — hpanel.hostinger.com. Billing, reboot, OS reinstall. Exposes SSH creds + browser terminal, so it grants server access too. David only.

Managing a VPS via an agent

For multi-step or exploratory work, SSH into the box first and launch the agent ON the VPS (e.g. codex --yolo), then talk to that local-on-server agent — it has full filesystem/process context and avoids fragile SSH round-trips. For short command sequences (update, config change, restart), driving an existing SSH session directly (e.g. via a cmux pane) is fine.

When checking on a remote/on-box agent, send David one concise status line each time: what it is doing and whether it is on track.

Claude Code cmux note: after Claude finishes, it may prefill a predicted next user message; that draft is Claude, not David speaking.

Agents on servers

OpenClaw → personal.openclaw (managed via Dokploy).
Hermes → private.hermes (Discord gateway). Setup/config docs in library/hermes/.
n8n → n8n.automations.

Hermes ops (on private.hermes)

hermes --version            # shows version + commits behind
hermes update               # auto-snapshots, updates deps, rebuilds web UI, restarts gateway itself
hermes gateway status|restart
journalctl --user -u hermes-gateway --since '5 min ago' --no-pager   # gateway logs (systemd USER service)

Default model lives in ~/.hermes/config.yaml under model.provider + model.default — NOT in .env. Change via hermes model (interactive) or edit the yaml directly, then hermes gateway restart to propagate to gateways.
npm EBADENGINE warnings during update (deps want Node >=24, box runs v22) are non-blocking — do not "fix" them.
Deeper docs (Discord/Slack/WhatsApp setup, file structure, vision config): library/hermes/.

More from this repository

same repository

agent-self-scheduling

adriannoes/awesome-vibe-coding

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop", "heartbeat". Covers external clocks (Claude Code, Codex, Pi) vs Hermes' built-in scheduler.

2026-07-0744

cmux

adriannoes/awesome-vibe-coding

MUST be read ANY time you interact with cmux in ANY way — listing/inspecting/creating/closing cmux workspaces, panes, or surfaces; reading or capturing pane/screen output; sending input or keys to a pane/surface; delegating to, polling, or checking on other agents running in cmux panes/surfaces; building or rearranging terminal layout; cmux browser automation; sending notifications/flashes/status/progress to the sidebar; editing cmux settings; or integrating an agent with cmux hooks. If your command starts with `cmux ` or touches a cmux workspace/pane/surface/agent, read this FIRST. Triggers on "cmux", "in this workspace", "this pane", "the other agent", "delegate to", "check on the agent", "send to the pane". macOS only (14.0+).

2026-07-0744

codex-goal-loop

adriannoes/awesome-vibe-coding

Explain and write effective instructions for OpenAI Codex's `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate). Use when the user mentions Codex `/goal`, "goal loop", "Ralph loop", wants to kick off a long-running autonomous Codex run, asks how to write a goal prompt, or wants a one-paragraph goal instruction drafted.

2026-07-0744

delegating-to-agents

adriannoes/awesome-vibe-coding

How to delegate work to another AI agent (Pi, Codex, Claude Code, Hermes) — picking the right agent, sending prompts to TUI agents, polling progress. Read BEFORE any `cmux send`/`tmux send-keys` to an agent, or whenever delegating, relaying, spawning, or orchestrating agent-to-agent work.

2026-07-0744

run-deep-swe

adriannoes/awesome-vibe-coding

Score any AI model on the DeepSWE coding-agent benchmark via the OpenRouter API. Use when the user wants an independent, reproducible coding-agent eval — "run DeepSWE", "benchmark this model on DeepSWE", "score model X on the coding benchmark", "test a model via OpenRouter on DeepSWE", or to verify vendor-reported coding scores. Covers setup, the OpenRouter wiring for mini-swe-agent, single-task / subset / full 113-task runs, and leaderboard submission.

2026-07-0744

anti-sleep

adriannoes/awesome-vibe-coding

Keep David's MacBook awake with macOS caffeinate — prevent sleep, screen dimming, or both, for a set duration or while a process runs. Use when the user says "don't let my mac sleep", "keep the screen on", "anti-sleep", "caffeinate", or wants the machine awake overnight / during a long build.

2026-07-0744

name	vps-server-management
description	Use when David wants to manage his VPS servers and the AI agents running inside them — connecting, deploying, monitoring, restarting, and operating remote hosts and their agents. Triggers on VPS, server management, remote host, SSH into server, manage my servers, agents on the server.

VPS Server Management

Source of truth: <path-to-infrastructure-doc>/infrastructure.md (read it for the latest — IPs/expirations change).

Servers (Hostinger VPS) — 3 total

Hostname	OS	Purpose
personal.openclaw	Ubuntu 24.04 (Dokploy)	OpenClaw — personal instance
n8n.automations	Ubuntu 24.04 (n8n)	All n8n workflow automations (primary)
private.hermes	Ubuntu 24.04	Hermes Agent — Discord gateway

SSH as root@<IP>.

Access levels (never share higher than needed)

App login — e.g. <n8n-app-hostname>. Build/edit workflows, no server access. Safest to share.
VPS SSH — root@<IP>. Docker, files, system config. Trusted technical people only.
Hostinger hPanel — hpanel.hostinger.com. Billing, reboot, OS reinstall. Exposes SSH creds + browser terminal, so it grants server access too. David only.

Managing a VPS via an agent

When checking on a remote/on-box agent, send David one concise status line each time: what it is doing and whether it is on track.

Claude Code cmux note: after Claude finishes, it may prefill a predicted next user message; that draft is Claude, not David speaking.

Agents on servers

OpenClaw → personal.openclaw (managed via Dokploy).
Hermes → private.hermes (Discord gateway). Setup/config docs in library/hermes/.
n8n → n8n.automations.

Hermes ops (on private.hermes)

hermes --version            # shows version + commits behind
hermes update               # auto-snapshots, updates deps, rebuilds web UI, restarts gateway itself
hermes gateway status|restart
journalctl --user -u hermes-gateway --since '5 min ago' --no-pager   # gateway logs (systemd USER service)

Default model lives in ~/.hermes/config.yaml under model.provider + model.default — NOT in .env. Change via hermes model (interactive) or edit the yaml directly, then hermes gateway restart to propagate to gateways.
npm EBADENGINE warnings during update (deps want Node >=24, box runs v22) are non-blocking — do not "fix" them.
Deeper docs (Discord/Slack/WhatsApp setup, file structure, vision config): library/hermes/.