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 instructions/strausmann/mcp-dockhand/claude-mdgit clone --depth 1 https://github.com/strausmann/mcp-dockhandWrote 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/instructions/strausmann/mcp-dockhand/claude-md)<a href="https://agentmods.dev/instructions/strausmann/mcp-dockhand/claude-md"><img src="https://agentmods.dev/badge/instructions/strausmann/mcp-dockhand/claude-md.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 | $0.01009 | $0.01009 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
mcp-dockhand CLAUDE.md 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mcp-dockhand CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — MCP-Dockhand Server
Projektübersicht
MCP Server (Model Context Protocol) für Dockhand Docker Management. Wrapt die Dockhand REST API in 130+ MCP-Tools mit Streamable HTTP Transport.
Tech Stack
- Runtime: Node.js 22+
- Sprache: TypeScript (strict mode)
- MCP SDK: @modelcontextprotocol/sdk
- Validierung: Zod (aktuell v3, Migration auf v4 geplant)
- Build:
npm run build(tsc) - Typecheck:
npm run typecheck - Tests: Vitest (geplant — siehe Issue für Test-Suite)
- Docker: Multi-stage Build, non-root User, Healthcheck
Verzeichnisstruktur
src/
├── index.ts # Entry Point, Express Server
├── server.ts # MCP Server Factory (Multi-Session)
├── auth/ # Dockhand Session-Authentifizierung
├── client/ # HTTP Client mit Cookie-Management
├── tools/ # Tool-Definitionen (130+)
│ ├── containers.ts # Container-Management (27 Tools)
│ ├── stacks.ts # Stack-Management (21 Tools)
│ ├── images.ts # Image-Management (9 Tools)
│ ├── networks.ts # Netzwerk-Management (7 Tools)
│ ├── volumes.ts # Volume-Management (9 Tools)
│ ├── git-stacks.ts # Git-Stack-Management (15 Tools)
│ ├── environments.ts # Environment-Management (18 Tools)
│ ├── users.ts # User/Rollen-Management (20 Tools)
│ ├── system.ts # System/Health/Metrics (19 Tools)
│ └── ... # Weitere Tool-Dateien
├── types/ # TypeScript-Typen
└── utils/ # Hilfsfunktionen
Konventionen
Code-Stil
- Alle Tool-Parameter mit Zod validieren
encodeURIComponent()auf ALLEN Pfad-Parametern (Container-IDs, Stack-Namen etc.)- Environment-ID als
environmentId(number) — IMMER als Query-Parameter?env= - Session-basierte Auth — automatisches Re-Login bei 401
- SSE für Deploy-Operationen (
postSSEMethode)
Tool-Definition Pattern
server.tool(
'tool_name',
'Beschreibung was das Tool tut',
{
environmentId: z.number().describe('Environment ID (required)'),
name: z.string().describe('Resource name'),
// Optionale Parameter:
option: z.string().optional().describe('Optional parameter'),
},
async ({ environmentId, name, option }) => {
const client = await getClient(session);
const result = await client.get(`/api/endpoint/${encodeURIComponent(name)}`, { env: environmentId });
return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
}
);
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.
- 5d ago First seen · 99 lines · 1,009 tokens per session scan A 111272dc41bd
mcp-dockhand CLAUDE.md is an instructions file published in the GitHub repository strausmann/mcp-dockhand (37 stars, last pushed today), licensed MIT. It adds 1,009 tokens to every session, about $0.0050 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 instructions, from other repositories
aks-mcp copilot-instructions.md
Copilot instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
better-notion-mcp CLAUDE.md
Claude Code instructions for n24q02m/better-notion-mcp, covering better-notion-mcp, cau truc, lenh thuong dung, test don le and mise shortcuts.
better-notion-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-notion-mcp, covering agents.md - better-notion-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
better-godot-mcp CLAUDE.md
Claude Code instructions for n24q02m/better-godot-mcp, covering claude.md - better-godot-mcp, commands, setup, lint & type check and fix.
better-godot-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-godot-mcp, covering agents.md - better-godot-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
homelab-mcp CLAUDE.md
Instructions for bjeans/homelab-mcp, covering claude development guide for homelab mcp, project overview, core philosophy, project structure and architecture patterns.