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.
npx skills add abdullahkhawer/devops-skills --skill hetzner-cligit clone --depth 1 https://github.com/abdullahkhawer/devops-skillsWrote 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.
[](https://agentmods.dev/skills/abdullahkhawer/devops-skills/hetzner-cli)<a href="https://agentmods.dev/skills/abdullahkhawer/devops-skills/hetzner-cli"><img src="https://agentmods.dev/badge/skills/abdullahkhawer/devops-skills/hetzner-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/abdullahkhawer/devops-skills/hetzner-cli"><img src="https://agentmods.dev/badge/skills/abdullahkhawer/devops-skills/hetzner-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00681 |
| Opus 5.5 | $0.00012 | $0.00272 |
| Sonnet 5.5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade B, and why
hetzner-cli 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 23d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- NEVER run any command in the "Never run" table above without explicit user instruction — a human must execute these, especially against production. How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hetzner Cloud CLI Skill
When running hcloud commands, always pass the --context flag based on the target environment.
Configuration
Update the context map below with your hcloud CLI context names:
| Environment | Context |
|---|---|
| Production | <your-prod-context> |
| Staging / Non-Prod | <your-nonprod-context> |
Prerequisites (one-time setup by user)
If not already authenticated, inform the user that setup is required and ask them to complete the following steps manually. Do not perform these steps yourself.
brew install hcloud
hcloud context create <your-context-name>
hcloud context list
Command Format
hcloud --context <context> <resource> <command> [options]
Examples
# Production
hcloud --context <your-prod-context> server list
# Staging / Non-Prod
hcloud --context <your-nonprod-context> server list
Available Commands
Read-only (safe, no confirmation needed)
| Command | Description |
|---|---|
server list / server describe <name> |
List or describe servers |
volume list / volume describe <name> |
List or describe volumes |
load-balancer list / load-balancer describe <name> |
List or describe load balancers |
network list / network describe <name> |
List or describe networks |
firewall list / firewall describe <name> |
List or describe firewalls |
context list / context active |
Show CLI context information |
Mutating operations (confirm with user before running)
| Command | Description |
|---|---|
server create |
Create a new server |
volume create |
Create a new volume |
load-balancer create |
Create a new load balancer |
server resize |
Resize a server |
Never run — requires explicit human approval
| Command | Reason |
|---|---|
server delete |
Irreversible resource deletion |
volume delete |
Irreversibly deletes a volume and its data |
load-balancer delete |
Irreversibly deletes a load balancer |
server reset / server poweroff |
Disrupts running workloads |
firewall delete |
Removes network security controls |
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.
- 23d ago First seen · 84 lines · 31 tokens per session scan B 30e88cb4510d
hetzner-cli is a skill published in the GitHub repository abdullahkhawer/devops-skills (8 stars, last pushed 24d ago), licensed Apache-2.0. It adds 31 tokens to every session and 681 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other skills, from other repositories
tianji-worker
Use when creating, testing, deploying, invoking, debugging, scheduling, pausing, or rolling back Tianji Workers, or managing their environment variables and shared modules.
docs-manage
Manage the Grounded Docs MCP Server documentation index. Covers scraping and indexing documentation from URLs or local files, refreshing existing indexes with changed content, removing libraries from the index, and compacting the SQLite store. Use when you need to add, update, or delete indexed documentation, or…
fetch-url
Fetch a single URL and convert its content to Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. The content is returned as plain Markdown text on stdout.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
dokploy-deploy
This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".
openship-config
This skill should be used when the user asks to "create openship.json", "configure an OpenShip deployment", "make a repo deployable on OpenShip", or fix "openship config validate" errors.