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 IsaiaScope/ai --skill hetzner-deletegit clone --depth 1 https://github.com/IsaiaScope/aiWrote 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/isaiascope/ai/hetzner-delete)<a href="https://agentmods.dev/skills/isaiascope/ai/hetzner-delete"><img src="https://agentmods.dev/badge/skills/isaiascope/ai/hetzner-delete.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 5.1 | $0.00112 | $0.01725 |
| Opus 5 | $0.00056 | $0.00863 |
| Sonnet 5 | $0.00022 | $0.00345 |
| Haiku 4.5 | $0.00011 | $0.00172 |
Grade A, and why
hetzner-delete scanned grade A with 0 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hetzner-delete
Destroy a server and remove the debris. The destroy itself is one hcloud call — the
value here is the guard rails around it and the six places it leaves orphans.
Invocation: /hetzner-delete <name> — a key under servers in the roster.
No default. Never operate on the fleet.default entry implicitly.
Sibling skills: /hetzner-create (provision) · /hetzner-ssh (connect).
hcloud server deletehas no confirmation prompt and no--forceflag. It takes a name and destroys the box immediately. Every safeguard below exists because the CLI provides none.
Step 0 — Resolve and check protection
cat ~/.config/hetzner/hetzner.json
| Condition | Action |
|---|---|
<name> not in servers |
Print available keys and stop. Never fuzzy-match a name. |
protected: true |
REFUSE. Print the message below and stop. Take no snapshot, touch nothing |
No <name> given |
Ask. Never assume, never fall back to fleet.default |
⛔ REFUSED — '<name>' is protected.
To delete it:
1. set "protected": false in fleet.servers.<name> of ~/.config/hetzner/hetzner.json
2. re-run this command
Nothing was touched.
The two-key rule is the point: unprotecting is a deliberate edit in another tool at another moment. Never offer to make that edit as part of this run — doing so collapses two keys into one and defeats the guard entirely.
Step 1 — Blast radius
Show exactly what dies and what survives. Read live state; do not trust the roster alone.
hcloud server describe <hcloud_server>
hcloud volume list -o noheader | grep <hcloud_server> || true
hcloud floating-ip list -o noheader | grep <hcloud_server> || true
hcloud firewall describe <firewall> -o 'format={{len .AppliedTo}}' 2>/dev/null
WILL DESTROY
server <name> <type>, <location>, up <N>d
disk <N> GB — all data on it
ip <ip> — released, NOT recoverable, may be reassigned to a stranger
volumes <list or none>
WILL KEEP
firewall <firewall> — shared, still attached to <N> other server(s)
ssh key <label> — shared across the fleet
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.
- 8d ago First seen · 183 lines · 112 tokens per session scan A eb1fba0495e0
hetzner-delete is a skill published in the GitHub repository IsaiaScope/ai (2 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,725 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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"…
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…
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...
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…
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…