Agent skill

Hetzner

by ericrisco in ericrisco/rsc-harness

A skill your agent uses when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and…

MITAuto-check: notesDevOps & Cloud

Install Hetzner

skills CLI
$ npx skills add ericrisco/rsc-harness --skill hetzner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ericrisco/rsc-harness hetzner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ericrisco/rsc-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hetzner .claude/skills/hetzner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hetzner
GitHub stars
167
Token cost
~2.6k tokens
SKILL.md length
1,102 words
Files
6 (incl. scripts, references)
Skills in repo
227
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and…

  • Hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX)
  • SKILL.md covers Decide before you create, Provision reproducibly, Two firewalls, in order and SSH hardening rules, plus 4 more sections
  • Runs Shell scripts from its folder; calls hcloud, ssh and docker
  • Bringing it up reproducibly with hcloud + cloud-init

What it does

Hetzner is an agent skill from ericrisco/rsc-harness. Use when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and wiring the Cloud Firewall to hand off a Docker-ready host. NOT app deploys on Coolify (that is coolify), NOT Dockerfiles (that is docker), NOT another provider (that is digitalocean).

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `evals/README.md`, `evals/cases.yaml` and `references/cloud-init.md`).

It sits in DevOps & Cloud, covering Containers. It works with Docker. The repository describes itself as: Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the… The licence is MIT.

When your agent uses it

  • Hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX)
  • Bringing it up reproducibly with hcloud + cloud-init
  • Locking down SSH
  • Wiring the Cloud Firewall to hand off a Docker-ready host

Example prompts

  • “/hetzner”

Requirements

  • A Bash shell
  • Docker

What it can do on your machine

Read from SKILL.md and the folder at commit e3d5b33. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • hcloud
    • ssh
    • docker
    • brew

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use ssh and docker, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hetzner loads about 2.6k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 1,102 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:135
    o root login.** `PermitRootLogin no` + a sudo user. Root over SSH is the
  • NoteRuns commands with sudoSKILL.md:181
    no`, `PasswordAuthentication no`, key + sudo user |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ericrisco/rsc-harness at commit e3d5b33, republished under its MIT licence (© ericrisco). 1,102 words, ~2,624 tokens.

Download SKILL.mdSave it as .claude/skills/hetzner/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
hetzner
description
Use when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and wiring the Cloud Firewall to hand off a Docker-ready host. NOT app deploys on Coolify (that is `coolify`), NOT Dockerfiles (that is `docker`), NOT another provider (that is `digitalocean`).
tags
hetzner, vps, cloud-firewall, hcloud, ssh-hardening, cloud-init, self-hosting
recommends
coolify, docker, secure-coding, domains-dns, backups, monitoring
origin
risco

Hetzner — the cheap European box, made safe and reproducible

Hetzner Cloud is chosen for one reason: price/performance. A 2 vCPU / 4 GB AMD box runs about €7.99/mo, the EU Intel line dips under €4, and EU locations include 20 TB of egress. The risk is that "cheap" becomes "unhardened and unmonitored" — a root-SSH box on a public IPv4 with password auth on. Your job is to make the cheap box safe and reproducible: every server comes up from a committed cloud-init file and a Cloud Firewall ruleset, never from click-ops in the console. A box you can't recreate from a file isn't a box, it's a pet.

Decide before you create

Pick the line, then the location. Prices are post-2026-04-01 (a price adjustment took effect that date); treat exact cents as "verify in the console."

LineChipWhen to pickPrice bandEU-only?
CXIntel (shared)Cost-optimized, tiny EU workloads~€3.99/mo (2 vCPU/4 GB/40 GB)Yes
CPXAMD (shared)Default for apps; best general valueCPX22 ~€7.99, CPX32 ~€13.99, CPX42 ~€25.49No
CAXARM64 (shared)Cheapest per-core; ARM-clean workloadsCheapest per-coreYes
CCXDedicated vCPUSteady CPU load, no noisy-neighborCCX13 ~€15.99 (2 vCPU/8 GB)No

Rules:

  • IPv4 costs extra (~€0.50–0.60/mo); IPv6 is free. An IPv6-only box is cheaper, but it breaks anything that can't reach IPv6: many container registries, some package mirrors, CI runners, SSH clients on IPv4-only nets. If docker pull or apt will run on the box, keep one IPv4 unless you've confirmed every upstream is dual-stack. Why: a saved €0.50/mo is not worth a broken docker pull at 2 a.m.
  • Location decides your traffic budget. EU locations (Nuremberg, Falkenstein, Helsinki) include 20 TB/mo egress; overage ~€1/TB. US (Ashburn, Hillsboro) and Singapore have far lower included transfer. Why: pick US "for latency," serve a video, and the surprise bill is the traffic cap, not the instance.
  • No APAC own datacenter. If your users are in Asia, this is a real latency cost — name it, don't hide it.

Full dated matrix, latency notes, and the no-SLA / no-managed-DB reality: references/plans-and-locations.md.

Provision reproducibly

Install the official CLI (latest v1.65.0, released 2026-05-21) and create a context (the token comes from the project's Security → API tokens, Read & Write):

bash
brew install hcloud            # or: see github.com/hetznercloud/cli releases
hcloud context create my-project   # paste the Read+Write API token when prompted
hcloud server-type list        # confirm names/prices before you create

Bring the box up with cloud-init so hardening happens before first login:

bash
hcloud server create \
  --name app-01 \
  --type cpx22 \
  --location fsn1 \
  --image debian-12 \
  --ssh-key my-laptop \
  --firewall app-edge \
  --user-data-from-file cloud-init.yaml

Use --location, not --datacenter: the datacenter attribute is deprecated and removed after 2026-07-01 for Servers and Primary IPs. Trimmed cloud-init skeleton (full annotated file in references/cloud-init.md):

yaml
#cloud-config
users:
  - name: deploy
    groups: [sudo]
    shell: /bin/bash
    sudo: ["ALL=(ALL) NOPASSWD:ALL"]
    ssh_authorized_keys:
      - ssh-ed25519 AAAA... you@laptop   # your real public key, not a placeholder
disable_root: true                       # no root login at all
ssh_pwauth: false                        # no password auth, anywhere
package_update: true
packages: [ufw, fail2ban, unattended-upgrades]
runcmd:
  - sed -i 's/^#\?PermitRootLogin.*/PermitRootLogin no/' /etc/ssh/sshd_config
  - sed -i 's/^#\?PasswordAuthentication.*/PasswordAuthentication no/' /etc/ssh/sshd_config
  - ufw default deny incoming && ufw allow 22 && ufw allow 80 && ufw allow 443 && ufw --force enable
  - systemctl enable --now fail2ban
  - systemctl restart ssh

Rule: never create a box with a bare root password and "I'll harden it later." Later is a window where the box is reachable as root with password auth on, and Hetzner IPv4 space is scanned constantly. Bake it into boot.

Two firewalls, in order

The Cloud Firewall runs at the network edge — stateful, applied before the packet reaches the VM, and survives a misconfigured host. Create and apply it with or before the server:

bash
hcloud firewall create --name app-edge
hcloud firewall add-rule app-edge --direction in --protocol tcp --port 22  --source-ips 0.0.0.0/0 --source-ips ::/0
hcloud firewall add-rule app-edge --direction in --protocol tcp --port 80  --source-ips 0.0.0.0/0 --source-ips ::/0
hcloud firewall add-rule app-edge --direction in --protocol tcp --port 443 --source-ips 0.0.0.0/0 --source-ips ::/0
hcloud firewall apply-to-resource app-edge --type server --server app-01

Inbound is default-deny — you only describe what you allow. Then the host ufw (set up in cloud-init above) is defense-in-depth: if you ever detach or fat-finger the Cloud Firewall, the box still isn't wide open. Why both: the edge firewall is your primary defense, but a single layer is a single point of failure, and the two are configured through different surfaces (API vs host).

Tighten SSH to your own IP/range once you know it:

bash
hcloud firewall delete-rule app-edge --direction in --protocol tcp --port 22 --source-ips 0.0.0.0/0 --source-ips ::/0
hcloud firewall add-rule    app-edge --direction in --protocol tcp --port 22 --source-ips 203.0.113.4/32

SSH hardening rules

  • Key-only auth. PasswordAuthentication no, PubkeyAuthentication yes. A password is brute-forceable; an ed25519 key is not.
  • No root login. PermitRootLogin no + a sudo user. Root over SSH is the single most-targeted login on the internet.
  • fail2ban on. Bans IPs after repeated failures — cheap insurance for the one port you must expose.
  • Moving port 22 is obscurity, not security. It quiets log noise; it does not harden anything. Do it if you like clean logs, but never instead of key-only
    • a firewall.
Show full SKILL.md (465 more words)Show less

Hand off to Docker / Coolify

"Host ready" means all of the following are true:

  • ssh root@<ip> is refused; ssh deploy@<ip> works with the key only.
  • sshd -T | grep -E 'permitrootlogin|passwordauthentication' shows both no.
  • Cloud Firewall attached; only 22 (scoped)/80/443 inbound.
  • ufw status enabled with the same allowlist.
  • unattended-upgrades and fail2ban running.

This skill stops at a clean, hardened host. Then route the install/deploy: coolify for the Coolify install + app deploy flow, docker for Dockerfiles, compose, and image hardening.

Day-2

  • Snapshot ≠ backup. A snapshot is a one-off manual image you can boot from; the Backups add-on is automated, rotating, ~20% of the server price. A snapshot you took once in March is not a backup strategy — for that, see backups.
  • Resize grows, never shrinks. You can scale the disk up; you cannot scale it back down. Size conservatively or you're stuck paying for it.
  • Volumes for data you want to outlive/detach from the server. Keep databases and uploads on a volume so a server rebuild doesn't take the data with it.
  • Reverse DNS must match for outbound mail to be accepted — set the PTR in the console/hcloud if the box sends email. Forward DNS records belong to domains-dns.
  • No SLA, no managed DB. There's no uptime guarantee, no managed-database product, and phone support only for dedicated-server customers — you run Postgres yourself, you monitor it yourself. For monitoring and alerting, see monitoring; treat the box as something you must watch, not something Hetzner watches for you. Name the trade-off to the user; don't pretend it's AWS.

Anti-patterns

Anti-patternWhy it's wrongDo instead
Root SSH + password auth left onThe most-scanned login on the public internet; bots find it in minutesPermitRootLogin no, PasswordAuthentication no, key + sudo user
Only host ufw, no Cloud FirewallA host misconfig or reset exposes everything; no edge layerCloud Firewall default-deny first, ufw as defense-in-depth
--source-ips 0.0.0.0/0 on everything "temporarily"Temporary rules become permanent; the whole box is exposedScope inbound to 80/443 public, SSH to your IP/range
Click-ops in the consoleNot reproducible — you can't recreate or review the boxcloud-init file + hcloud commands committed to the repo
Snapshot treated as backupOne stale manual image, no rotation, no scheduleEnable the Backups add-on or push to off-box storage
US location, then surprised by the billUS/Singapore include far less than EU's 20 TB egressEU location for egress-heavy apps; check the traffic cap first
IPv6-only to save €0.50Registry/CI/mirror pulls over IPv4-only breakKeep one IPv4 unless every upstream is confirmed dual-stack
Using --datacenterDeprecated, removed after 2026-07-01Use --location

Verify

bash
ssh -o BatchMode=yes root@<ip>                 # expect: refused / permission denied
ssh deploy@<ip> 'sshd -T | grep -E "permitrootlogin|passwordauthentication"'
# expect: permitrootlogin no / passwordauthentication no
hcloud firewall describe app-edge              # expect: only 22 (scoped)/80/443 inbound
ssh deploy@<ip> 'ss -tlnp'                      # expect: only expected listeners

To lint a cloud-init / hardening file before you ever create the box, run scripts/verify.sh path/to/cloud-init.yaml — it statically checks for the must-haves (no root login, no password auth, an SSH key, a firewall step, fail2ban) with no network calls.

© ericrisco, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in skills/hetzner of ericrisco/rsc-harness.

  • SKILL.md
  • evals/README.md
  • evals/cases.yaml
  • references/cloud-init.md
  • references/plans-and-locations.md
  • scripts/verify.sh

Open the folder on GitHubat commit e3d5b33

Compare with similar skills

Hetzner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hetzner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hetzner this skillericrisco/rsc-harness167—~2.6kAutomated safety check: NotesMIT
Iron Proxy Gateway for NanoClawnanocoai/nanoclaw31k—~4.6kAutomated safety check: NotesMIT
GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb6.7k—~4kAutomated safety check: NotesApache-2.0
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2606 repos~1.1kAutomated safety check: NotesCustom licence
LangBot Deployment Guidelangbot-app/LangBot18k—~1.2kAutomated safety check: NotesApache-2.0
Build Openshell Mxc WindowsNVIDIA/OpenShell15k—~4.9kAutomated safety check: PassApache-2.0

Similar skills

  • Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.

    31k GitHub stars~4.6k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • GreptimeDB Dev Docker Image

    GreptimeTeam/greptimedb

    Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.

    6.7k GitHub stars~4k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Senior DevOps Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…

    260 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • LangBot Deployment Guide

    langbot-app/LangBot

    Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.

    18k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Official

    Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64.

    15k GitHub stars~4.9k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Omnigent Docker Compose Deploy

    omnigent-ai/omnigent

    Brings up the Omnigent server and Postgres as a Docker compose stack on any Docker host, and covers the Dockerfile's runtime and host build targets for extending it to a new platform.

    11k GitHub stars~1.3k tokensUpdated today
    DevOps & CloudAuto-check: notes

More from ericrisco/rsc-harness

All 227 skills in this repo
  • Ab Testing

    ericrisco/rsc-harness

    A skill your agent uses when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go…

    167 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Accessibility

    ericrisco/rsc-harness

    A skill your agent uses when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast…

    167 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Ads

    ericrisco/rsc-harness

    A skill your agent uses when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platform-fit creative, budget/scaling rules…

    167 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Agent Eval

    ericrisco/rsc-harness

    A skill your agent uses when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual…

    167 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • AI Media

    ericrisco/rsc-harness

    A skill your agent uses when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with…

    167 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Analytics

    ericrisco/rsc-harness

    A skill your agent uses when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing.

    167 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Hetzner

What does Hetzner do?

A skill your agent uses when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and…. Hetzner is an agent skill from ericrisco/rsc-harness. Use when provisioning or hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX), bringing it up reproducibly with hcloud + cloud-init, locking down SSH, and wiring the Cloud Firewall to hand off a Docker-ready host.

When should I use Hetzner?

Hetzner fits situations like: hardening a Hetzner Cloud VPS: picking the plan/location (CX/CPX/CAX/CCX); bringing it up reproducibly with hcloud + cloud-init; locking down SSH; wiring the Cloud Firewall to hand off a Docker-ready host.

How do I install Hetzner in Claude Code?

Run `npx skills add ericrisco/rsc-harness --skill hetzner -a claude-code`. Or copy the skill folder (skills/hetzner in ericrisco/rsc-harness) into .claude/skills/hetzner in your project. Claude Code loads it when a task matches its description.

How do I install Hetzner in Codex?

Run `npx skills add ericrisco/rsc-harness --skill hetzner -a codex`. Or copy the skill folder (skills/hetzner in ericrisco/rsc-harness) into .agents/skills/hetzner in your project. Codex loads it when a task matches its description.

Can I use Hetzner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ericrisco/rsc-harness --skill hetzner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hetzner, .gemini/skills/hetzner, .github/skills/hetzner and .opencode/skills/hetzner in your project.

What does Hetzner need to run?

Going by SKILL.md and its folder, Hetzner needs a shell for the scripts in its folder and the command-line tools its instructions call (hcloud, ssh, docker and brew). Our summary lists: A Bash shell; Docker.

Does Hetzner access the network?

SKILL.md contains no URLs. Its commands use ssh and docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Hetzner safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Hetzner use?

Hetzner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hetzner use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Hetzner?

Skills that share tags, products or a category with Hetzner: Iron Proxy Gateway for NanoClaw (nanocoai/nanoclaw, 31k stars), GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 260 stars) and LangBot Deployment Guide (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hetzner?

ericrisco (a GitHub user) maintains it in ericrisco/rsc-harness, which has 167 GitHub stars. The repository holds 227 skills in this directory. The repository was last updated on October 7, 2026.

Source: ericrisco/rsc-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.