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/kastelldev/kastell/kastell-opsnpx skills add kastelldev/kastell --skill kastell-opsgit clone --depth 1 https://github.com/kastelldev/kastellWrote 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/kastelldev/kastell/kastell-ops)<a href="https://agentmods.dev/skills/kastelldev/kastell/kastell-ops"><img src="https://agentmods.dev/badge/skills/kastelldev/kastell/kastell-ops.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 | $0.00053 | $0.01501 |
| Opus 5 | $0.00026 | $0.00750 |
| Sonnet 5 | $0.00011 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
kastell-ops 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 6d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kastell Architecture
Kastell is a CLI toolkit for provisioning, securing, and managing self-hosted servers. TypeScript, ESM, strict mode. CLI commands, first-party MCP tools, 4 cloud providers (hetzner, digitalocean, vultr, linode), 2 platform adapters (coolify, dokploy).
Live Context
Version: !node -e "import('fs').then(f=>console.log(JSON.parse(f.readFileSync('package.json','utf8')).version)).catch(()=>console.log('unknown'))"
Registered servers:
!kastell list 2>/dev/null || echo "No servers registered"
Architecture File Map
src/
commands/ # 31 thin CLI wrappers (parse args + delegate only)
core/ # Business logic (ALL computation here)
providers/ # Cloud API: hetzner, digitalocean, vultr, linode
adapters/ # Platform abstraction: coolify, dokploy
interface.ts # PlatformAdapter contract
factory.ts # getAdapter(), detectPlatform(), resolvePlatform()
mcp/
server.ts # 13 tool registrations
tools/ # Handler files (Zod schema + handler per tool)
utils/ # ssh, config, cloudInit, modeGuard, migration
types/ # ServerMode, ServerRecord, Platform
constants.ts # PROVIDER_REGISTRY (single source of truth)
index.ts # CLI entry point
Layer Rules
| Layer | Path | Responsibility | Rule |
|---|---|---|---|
| Commands | src/commands/ | Parse CLI args, call core, display output | ZERO business logic |
| Core | src/core/ | All business logic, orchestration | No UI/chalk/ora imports |
| Providers | src/providers/ | Cloud API calls per provider | Implements cloud CRUD |
| Adapters | src/adapters/ | Platform-specific ops (Coolify/Dokploy) | Via PlatformAdapter interface |
| MCP | src/mcp/ | MCP server + tool handlers | Delegates to core |
| Utils | src/utils/ | SSH, config, modeGuard, errorMapper | Shared infrastructure |
What ships with it
7 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.
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.
- 6d ago First seen · 140 lines · 53 tokens per session scan A 81377613fefc
kastell-ops is a skill published in the GitHub repository kastelldev/kastell (60 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,501 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
coolify
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is railway), NOT sizing/hardening the box (that is hetzner), NOT…
hetzner
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…
app-deployment
Deploy applications via git-push-to-deploy workflow - set up production remotes, push code, manage environment variables, restart containers. Triggers on phrases like "deploy an app", "deploy this app", "push code to server", "set up deployment", "git push deploy", "restart app", "copy env to server", "set up…
dns-management
Manage Cloudflare DNS records - list zones and records, add/update A records, remove records. Discovers domains dynamically from Cloudflare. Triggers on phrases like "add DNS record", "remove DNS", "list DNS", "Cloudflare DNS", "add subdomain", "point domain to server", "what domains do I have", "list zones".
server-management
Manage Hetzner Cloud servers - create, list, get IPs, and destroy servers. Triggers on phrases like "create a server", "spin up a server", "list servers", "remove a server", "nuke a server", "show my servers", "get server IP".
server-bootstrap
Bootstrap and configure servers for Docker deployments - install Docker, set up Caddy reverse proxy, create deploy user, and configure unattended upgrades. Triggers on phrases like "bootstrap a server", "set up a server", "configure a server", "install Docker", "set up Caddy", "update deployer".