server-control

A skill for controlling a remote Linux computer over SSH, a secure connection used to run commands on another machine. It covers services, Docker, files, and logs.

In plain words
What is it for?
It helps run server commands, check status, restart services, edit remote files, manage Docker, inspect logs, and deploy changes. It requires server connection details.
Why use it?
It gives the agent a defined workflow for connecting to a server and handling common administration tasks remotely.

Skill for Claude CodeCodex

Part of the server-control plugin — 1 skill, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/d0raka/claude-server-control-plugin/server-control
Any agent
npx skills add d0raka/claude-server-control-plugin --skill server-control
Clone the repo
git clone --depth 1 https://github.com/d0raka/claude-server-control-plugin

Made for: Claude Code, Codex.

Or install server-control, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,120 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. Scan, not verified.
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 $0.00091 $0.01120
Opus 5 $0.00046 $0.00560
Sonnet 5 $0.00018 $0.00224
Haiku 4.5 $0.00009 $0.00112

Measured 2d ago against content hash c8697de36285, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

server-control 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 2d 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 -s localhost:PORT/health

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run([sys.executable, '-m', 'pip', 'install', 'paramiko', '--break-system-packages', '-q'])
skills/server-control/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Server Control — Linux via SSH

Other platforms: See SKILL-mac.md for macOS, SKILL-windows.md for Windows. To activate a different platform, rename its file to SKILL.md.


⚙️ SETUP — Fill in your details

Placeholder Replace with
YOUR_SERVER_IP Tailscale IP recommended (e.g. 100.64.0.5)
YOUR_USERNAME SSH user (e.g. ubuntu, pi, myuser)
YOUR_PASSWORD SSH password — or use key auth below

FIRST ACTION — connect silently on load

Run this before responding to the user:

import subprocess, sys
try:
    import paramiko
except ImportError:
    subprocess.run([sys.executable, '-m', 'pip', 'install', 'paramiko', '--break-system-packages', '-q'])
    import paramiko

client = paramiko.SSHClient()
client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
client.connect('YOUR_SERVER_IP', username='YOUR_USERNAME', password='YOUR_PASSWORD', timeout=10)
stdin, stdout, _ = client.exec_command('echo "connected: $(hostname) | $(date)"')
print(stdout.read().decode())
client.close()

✅ Success → continue normally. ❌ Failure → tell user: "Can't connect. Check that Tailscale is running and the server is online."


SSH Details

Host     : YOUR_SERVER_IP
User     : YOUR_USERNAME
Password : YOUR_PASSWORD
Port     : 22

Key-based auth (more secure):

client.connect('YOUR_SERVER_IP', username='YOUR_USERNAME',
               key_filename='/path/to/private_key', timeout=10)

Command Pattern — use for everything

import paramiko

def run(cmd, timeout=60):
    client = paramiko.SSHClient()
    client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
    client.connect('YOUR_SERVER_IP', username='YOUR_USERNAME', password='YOUR_PASSWORD', timeout=10)
    stdin, stdout, stderr = client.exec_command(cmd, timeout=timeout)
    out = stdout.read().decode().strip()
    err = stderr.read().decode().strip()
    client.close()
    return out if out else err

print(run('df -h && free -h && uptime'))
print(run('docker ps'))
print(run('systemctl status nginx'))

Read the full file on GitHub · 180 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 180 lines · 91 tokens per session scan A c8697de36285

Subscribe to this mod's changes

server-control is a skill published in the GitHub repository d0raka/claude-server-control-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 91 tokens to every session and 1,120 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

cross-platform-cloud-verification

Orchestrates cost-conscious cloud verification across available operating-system and architecture runners after cheaper checks pass. Use whenever a code change, bug fix, build, packaging flow, native dependency, UI behavior, filesystem behavior, or test has material cross-platform implications, even if the user only…

warpdotdev/warp · 92 tokens

olares-cluster

Olares ControlHub K8s runtime view via olares-cli cluster — inspect pods, containers, workloads, logs, jobs, cronjobs, namespaces, nodes, and middleware; exec, scale, restart, or delete K8s objects. Use for raw runtime objects and logs, not app lifecycle (market), resource metrics (dashboard), or host install.

beclab/Olares · 77 tokens

kubernetes-skill

Production-grade Kubernetes guidance (KubeShark). Activates for any task involving Kubernetes manifests, Helm charts, Kustomize overlays, RBAC, NetworkPolicies, or cluster operations. Enforces a failure-mode workflow with Conditional Reference Retrieval.

ArthurVardevanyan/HomeLab · 53 tokens

cloudflared

Cloudflare Tunnel CLI for exposing local services.

thewolffish/wolffish-app · 12 tokens

openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox…

NVIDIA/OpenShell · 127 tokens

cloud-k8s

Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.

zhaoxuya520/reverse-skill · 35 tokens