hetzner-ssh

hetzner-ssh is a skill for Claude Code, Codex from IsaiaScope/ai. It costs 136 tokens per session (2,941 once invoked), scanned B, original, MIT.

An SSH connection setup for reaching a Hetzner VPS, a rented virtual server, using the machine list and security settings stored in a local roster. It verifies that the connection reached the intended server and leaves a reusable connection open.

In plain words
What is it for?
It helps connect to a listed server, authenticate with its stored key, confirm the host identity, and prepare a low-overhead connection for later work.
Why use it?
It avoids manually finding server details, unlocking keys, and reconnecting for every command. Verification reduces the risk of working on the wrong machine.

Skill for Claude CodeCodex

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/isaiascope/ai/hetzner-ssh
Any agent
npx skills add IsaiaScope/ai --skill hetzner-ssh
Clone the repo
git clone --depth 1 https://github.com/IsaiaScope/ai

Made for: Claude Code, Codex.

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 hetzner-ssh

README.md
[![agentmods](https://agentmods.dev/badge/skills/isaiascope/ai/hetzner-ssh.svg)](https://agentmods.dev/skills/isaiascope/ai/hetzner-ssh)
Your own site
<a href="https://agentmods.dev/skills/isaiascope/ai/hetzner-ssh"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/hetzner-ssh.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,941 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00136 $0.02941
Opus 5 $0.00068 $0.01470
Sonnet 5 $0.00027 $0.00588
Haiku 4.5 $0.00014 $0.00294

Measured 5d ago against content hash 0674cacb4157, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

hetzner-ssh scanned grade B with 1 finding 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 5d 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 rootmediumPrivilege escalation

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

ssh <ssh_alias> 'sudo systemctl …' # sudo is passwordless on boxes hetzner-create built
skills/hetzner-ssh/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hetzner-ssh

Connect to a Hetzner VPS, prove it is the right one, and leave a live multiplexed connection behind so every later command is cheap. Hosts are hardened: non-standard sshd port, key-only auth, AllowUsers allowlist, Hetzner Cloud Firewall in front.

Invocation: /hetzner-ssh [server]server is a key under servers in the roster. Omit it to use the fleet.default entry.

Sibling skills: /hetzner-create (provision a new box) · /hetzner-delete (destroy one). The roster schema is documented once, in hetzner-create/README.md.


Step 0 — Load the roster

cat ~/.config/hetzner/hetzner.json

($CLAUDE_SKILL_DIR is not set in Claude Code — use the literal path above.)

Condition Action
File missing If you sync ~/.config/hetzner/ with a dotfiles manager, restore it there first (chezmoi apply ~/.config/hetzner/). Otherwise copy it from another machine, or run /hetzner-create to register a server. Stop.
Invalid JSON Report the parse error and the offending line. Do not guess the contents. Stop.
Requested server not in fleet.servers Print the available fleet.servers keys and stop. Never guess a neighbouring name.
No arg and no fleet.default key Print the available keys and ask which one. Stop.

Resolve the target: the user-supplied name, else .default. Fields missing from a server entry fall back to defaults — so a lean entry is normal, not broken. Every field below comes from the merged result; do not re-discover any of it.

Field Meaning
ssh_alias Host alias in ~/.ssh/config.d/hetzner — the actual connect target
expect_hostname What hostname must print, or you are on the wrong box
ip, port, user Rendered into the ssh_config block
key, key_fingerprint_prefix Which key, and how to spot it in the agent
protected Read by /hetzner-delete. Irrelevant here
hcloud_*, location, firewall Only used on the failure paths below
notes Free text: panel ports, runbook paths, quirks

Read the full file on GitHub · 206 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. 5d ago First seen · 206 lines · 136 tokens per session scan B 0674cacb4157

Subscribe to this mod's changes

hetzner-ssh is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed yesterday), licensed MIT. It adds 136 tokens to every session and 2,941 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

neo-azure-pipelines

Use this skill when the user asks to create, review, debug, or modernize Azure Pipelines YAML for CI/CD, especially .NET builds, Azure App Service deploys, or IIS/on-premises deploys. Prefer bundled templates and verify task syntax against Microsoft docs when version-specific accuracy matters.

Benknightdark/neo-skills · 66 tokens

vercel-hygiene

Audit and harden the 4 pivoshenko brand sites on Vercel (pivoshenko.dev, pivoshenko.startpage, pivoshenko.wallpapers, pivoshenko.ai), team pivoshenko. Read-only sweep -> per-site report (ok/attention/action) -> confirmed fixes. Emphasizes security headers and analytics coverage. Use when the user says "audit vercel"…

pivoshenko/pivoshenko.ai · 162 tokens

cloudflare-hygiene

Audit + harden + optimize live Cloudflare zones/domains — read-only sweep of each zone (SSL/TLS mode, HSTS, min TLS, TLS 1.3, Always-Use-HTTPS, Brotli, HTTP/3, 0-RTT, Early Hints, caching, security level, Bot Fight Mode, WAF, DNS proxy/TTL + SPF/DKIM/DMARC hygiene, DNSSEC) -> ok/attention/action report grouped by…

pivoshenko/pivoshenko.ai · 220 tokens

agent-framework-azure-ai-py

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code int...

majiayu000/claude-skill-registry · 48 tokens

agent-framework-azure-ai-py

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming…

majiayu000/claude-skill-registry · 79 tokens

agent-framework-azure-ai-py

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming…

majiayu000/claude-skill-registry · 79 tokens