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.
/plugin marketplace add kastelldev/kastellnpx agentmods add plugins/kastelldev/kastell/kastellgit clone --depth 1 https://github.com/kastelldev/kastellGrade A, and why
kastell 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 2d 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.
What it actually says
{
"name": "kastell",
"version": "2.3.1",
"description": "Server security auditing, hardening, and fleet management. Runtime-derived audit catalog, CIS/PCI-DSS/HIPAA compliance, production hardening workflows, and first-party MCP tools. Supports Hetzner, DigitalOcean, Vultr, Linode with Coolify, Dokploy, and bare VPS modes.",
"author": {
"name": "kastelldev",
"email": "[email protected]",
"url": "https://kastell.dev"
},
"homepage": "https://kastell.dev",
"repository": "https://github.com/kastelldev/kastell",
"license": "Apache-2.0",
"keywords": [
"server",
"security",
"audit",
"hardening",
"mcp",
"infrastructure",
"vps",
"cloud",
"hetzner",
"digitalocean",
"vultr",
"linode",
"coolify",
"dokploy",
"fleet"
],
"skills": "./kastell-plugin/skills/",
"hooks": "./kastell-plugin/hooks/hooks.json",
"mcpServers": {
"kastell": {
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/dist/mcp-bundle.mjs"
],
"env": {
"HETZNER_TOKEN": "${HETZNER_TOKEN}",
"DIGITALOCEAN_TOKEN": "${DIGITALOCEAN_TOKEN}",
"VULTR_TOKEN": "${VULTR_TOKEN}",
"LINODE_TOKEN": "${LINODE_TOKEN}",
"KASTELL_SAFE_MODE": "true"
}
}
}
}
What ships with it
1 file beside plugin.json 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.
- 2d ago First seen · 48 lines scan A b8c0ca7c6055
kastell is a plugin published in the GitHub repository kastelldev/kastell (59 stars, last pushed 16d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
marina-skill
Claude Code skills for managing Hetzner servers, Cloudflare DNS, and Docker deployments.
claude-code-plugin
Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.
hal-9000
Plugin marketplace listing 3 plugins: hal-voice, hal-session-auto-rename, hal-skills.
better-telegram-mcp
Telegram dual-mode (Bot API + MTProto) — messages, chats, media, contacts.
synapse
MCP server and CLI for host and container operations: Docker and Compose control, SSH, host inspection, logs, ZFS, and safe file transfer.
synapse
MCP server and CLI for host and container operations: Docker and Compose control, SSH, host inspection, logs, ZFS, and safe file transfer.