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 agentmods add skills/fcakyon/claude-codex-settings/hetzner-deploynpx skills add fcakyon/claude-codex-settings --skill hetzner-deploygit clone --depth 1 https://github.com/fcakyon/claude-codex-settingsWrote 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/fcakyon/claude-codex-settings/hetzner-deploy)<a href="https://agentmods.dev/skills/fcakyon/claude-codex-settings/hetzner-deploy"><img src="https://agentmods.dev/badge/skills/fcakyon/claude-codex-settings/hetzner-deploy.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.02203 |
| Opus 5 | $0.00034 | $0.01102 |
| Sonnet 5 | $0.00013 | $0.00441 |
| Haiku 4.5 | $0.00007 | $0.00220 |
Grade D, and why
hetzner-deploy scanned grade D with 3 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 4d 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.
sudo tar -C /usr/local/bin --no-same-owner -xzf hcloud-linux-amd64.tar.gz hcloud Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
hcloud ssh-key create --name deploy-key --public-key-from-file ~/.ssh/id_ed25519.pub Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sSLO https://github.com/hetznercloud/cli/releases/latest/download/hcloud-linux-amd64.tar.gz How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hetzner Cloud CLI Skill
Skill for provisioning and managing infrastructure on Hetzner Cloud using the hcloud CLI. Use the decision trees below to find the right command group, then load detailed references.
Your knowledge of Hetzner Cloud pricing, server types, locations, and API behavior may be outdated. Prefer retrieval over pre-training when citing specific numbers, available types, or configuration options. The reference files alongside this skill are starting points extracted from the official CLI docs.
Authentication
The CLI authenticates via API token. Set the HCLOUD_TOKEN environment variable or create a named context:
# Stateless (CI, scripting, agent use)
export HCLOUD_TOKEN="your-api-token"
# Named context (interactive use)
hcloud context create my-project
Generate tokens at https://console.hetzner.cloud under your project's Security > API Tokens.
Installation
# macOS / Linux (Homebrew)
brew install hcloud
# Linux (binary)
curl -sSLO https://github.com/hetznercloud/cli/releases/latest/download/hcloud-linux-amd64.tar.gz
sudo tar -C /usr/local/bin --no-same-owner -xzf hcloud-linux-amd64.tar.gz hcloud
# Docker
docker run --rm -e HCLOUD_TOKEN="$HCLOUD_TOKEN" hetznercloud/cli:latest <command>
Quick Decision Trees
"I need compute"
Need a server?
├─ Create a new server → hcloud server create --name <n> --type <t> --image <img>
├─ With cloud-init user data → add --user-data-from-file <path>
├─ With firewall + network → add --firewall <fw> --network <net>
├─ List available types → hcloud server-type list
├─ List available images → hcloud image list
├─ SSH into server → hcloud server ssh <name>
├─ Create snapshot → hcloud server create-image --type snapshot <name>
├─ Rescue mode → hcloud server enable-rescue <name>
└─ Delete server → hcloud server delete <name>
"I need networking"
Need networking?
├─ Private network (VPC) → hcloud network create --name <n> --ip-range <cidr>
│ ├─ Add subnet → hcloud network add-subnet --network <n> --type cloud --network-zone <z> --ip-range <cidr>
│ └─ Attach server → hcloud server attach-to-network --network <n> --server <s>
├─ Firewall → hcloud firewall create --name <n> --rules-file <json>
│ ├─ Apply to server → hcloud firewall apply-to-resource --firewall <n> --type server --server <s>
│ └─ Replace rules → hcloud firewall replace-rules --rules-file <json> <name>
├─ Load balancer → hcloud load-balancer create --name <n> --type <t> --location <loc>
│ ├─ Add target → hcloud load-balancer add-target --server <s> <lb>
│ └─ Add service → hcloud load-balancer add-service --protocol <p> --listen-port <port> <lb>
├─ Floating IP → hcloud floating-ip create --type ipv4 --home-location <loc>
│ └─ Assign → hcloud floating-ip assign <ip> --server <s>
└─ Primary IP → hcloud primary-ip create --name <n> --type ipv4 --datacenter <dc>
What ships with it
36 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.
- references/all/commands.md 1.6 KB
- references/all/README.md 1.1 KB
- references/certificate/commands.md 10 KB
- references/certificate/README.md 1.7 KB
- references/config/commands.md 16 KB
- references/config/README.md 1.1 KB
- references/dns/commands.md 42 KB
- references/dns/README.md 2.6 KB
- references/firewall/commands.md 17 KB
- references/firewall/README.md 2.1 KB
- references/floating-ip/commands.md 15 KB
- references/floating-ip/README.md 2.2 KB
- references/getting-started/configuration.md 1.3 KB
- references/getting-started/create-a-server.md 2.9 KB
- references/getting-started/output-options.md 4.3 KB
- references/getting-started/setup.md 7.3 KB
- references/image/commands.md 9.9 KB
- references/image/README.md 1.6 KB
- references/info/commands.md 18 KB
- references/info/README.md 1.2 KB
- references/load-balancer/commands.md 33 KB
- references/load-balancer/README.md 3.5 KB
- references/network/commands.md 19 KB
- references/network/README.md 2.5 KB
- references/placement-group/commands.md 9.0 KB
- references/placement-group/README.md 1.7 KB
- references/primary-ip/commands.md 16 KB
- references/primary-ip/README.md 2.2 KB
- references/server/commands.md 44 KB
- references/server/README.md 4.0 KB
- references/ssh-key/commands.md 8.8 KB
- references/ssh-key/README.md 1.5 KB
- references/storage-box/commands.md 47 KB
- references/storage-box/README.md 2.9 KB
- references/volume/commands.md 15 KB
- references/volume/README.md 1.9 KB
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.
- 4d ago First seen · 230 lines · 67 tokens per session scan D 1d2c878b7250
hetzner-deploy is a skill published in the GitHub repository fcakyon/claude-codex-settings (1,125 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 2,203 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
lov-maintain-partners
Maintain the Skill Publisher website's partners section AND align partner logo rows on event posters / hero strips: reuse lov-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets…
dsh-plugin-publisher
Publish a validated DSH plugin package (@deepseek-ai/dsh- or @lovstudio/dsh-) to npm, git, or tarball channels and verify it loads in the DeepSeek Harness. Use when the user asks to publish, release, or ship a plugin. 触发:发布插件 / 上架插件 / release dsh 插件。.
lov-deploy-to-vercel
Deploy frontend projects to Vercel with automatic custom domain setup. Handles Vite, Next.js, CRA, and static sites. Auto-configures Cloudflare DNS CNAME records and Vercel domain aliases. Supports SPA routing via vercel.json. Trigger when user says "deploy to vercel", "部署到 vercel", "vercel deploy", or mentions a…
lov-image-translation-errata
核对截图中的原文与机翻,生成保留错误痕迹、给出正确译文且尽量维持原布局的勘误图;用于“图片翻译勘误”“指出机翻错误”和 create an in-image translation errata。.
lov-media-crawler
给定视频号、小红书、抖音、快手、B站、微博、贴吧或知乎链接,复用登录态解析并高速下载媒体,返回可验证文件与诊断报告;适用于“下载这个视频链接”、"download this media link"。.