agentmods.dev

mcp-dockhand copilot-instructions.md

mcp-dockhand copilot-instructions.md is an instructions file for GitHub Copilot from strausmann/mcp-dockhand. It costs 758 tokens per session, scanned A, original, MIT.

Instructions for an MCP server that connects AI tools to Dockhand, a Docker management service. The server wraps Dockhand’s REST API, which is a web interface for sending requests and receiving data.

In plain words
What is it for?
Reviewing or implementing MCP tools for Docker management, verifying HTTP methods and data formats, and checking Hawser-related integrations.
Why use it?
They require checking Dockhand’s source code so tool methods, request fields, responses, and agent protocols match the real service.

Instructions file for GitHub Copilot

not rated 34 today A scan 758 tokens original MIT
View the source file strausmann/mcp-dockhand
Install

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.

agentmods
npx agentmods add instructions/strausmann/mcp-dockhand/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/strausmann/mcp-dockhand

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for mcp-dockhand copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/strausmann/mcp-dockhand/copilot-instructions.svg)](https://agentmods.dev/instructions/strausmann/mcp-dockhand/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/strausmann/mcp-dockhand/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/strausmann/mcp-dockhand/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 758 This file is loaded in full into every session.
When invoked 758 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 4d ago against content hash 7ffcc0975cd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-dockhand copilot-instructions.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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/copilot-instructions.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — MCP-Dockhand

Project Context

This is a Model Context Protocol (MCP) server for Dockhand Docker Management. It wraps the Dockhand REST API into 130+ MCP tools using Streamable HTTP transport.

Upstream repositories (source of truth for API behavior):

Critical: Verify Against Upstream

When reviewing MCP tool implementations, always cross-reference with the upstream Dockhand source code:

  1. HTTP Methods: Check src/routes/api/**/+server.ts in finsys/dockhand for the correct HTTP method (GET/POST/PUT/DELETE/PATCH). Our MCP tools MUST match.
  2. Request Body Fields: Check the actual request parsing in the Dockhand route handlers to verify parameter names and types match what our tools send.
  3. Response Format: Verify our tools correctly handle the response structure (JSON object vs array, pagination, error format).
  4. Hawser Protocol: For environment/hawser-related tools, check internal/protocol/messages.go and internal/docker/compose.go in finsys/hawser.
  5. API Schema: Compare against docs/dockhand-api-schema.json (auto-generated daily from upstream source).

If a tool's implementation differs from upstream, flag it as HIGH priority.

Code Review Guidelines

Security

  • All path parameters MUST use encodePath() from src/utils/encode-path.ts
  • No hardcoded credentials or tokens
  • Session cookies must not be logged
  • Environment filter must be applied on all environment-scoped endpoints
  • additionalConfig/additionalSettings must be merged BEFORE explicit fields (not after)

MCP Tool Quality

  • All parameters must have Zod validation with .describe() annotations
  • Tool descriptions must be clear and actionable for LLMs
  • Prefer explicit typed parameters over generic Record<string, unknown>
  • Required vs optional parameters must match the Dockhand API
  • connectionType gating: host/port only for hawser-standard, not hawser-edge

Read the full file on GitHub · 65 lines

Changes

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.

  1. 4d ago First seen · 65 lines · 758 tokens per session scan A 7ffcc0975cd3

Subscribe to this mod's changes

mcp-dockhand copilot-instructions.md is an instructions file published in the GitHub repository strausmann/mcp-dockhand (34 stars, last pushed today), licensed MIT. It adds 758 tokens to every session, about $0.0038 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.

Code reviewSecuritydockerdocker-managementdockhandmcpmcp-servermodel-context-protocol
Related

Other instructions, from other repositories

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.

n24q02m/better-notion-mcp · 2,316 tokens

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.

n24q02m/better-notion-mcp · 1,236 tokens

better-godot-mcp CLAUDE.md

Instructions for n24q02m/better-godot-mcp, covering claude.md - better-godot-mcp, commands, setup, lint & type check and fix.

n24q02m/better-godot-mcp · 1,423 tokens

better-godot-mcp 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.

n24q02m/better-godot-mcp · 1,043 tokens

mnemo-mcp AGENTS.md

Instructions for n24q02m/mnemo-mcp, covering agents.md - mnemo-mcp, commands, setup, lint & type check and fix.

n24q02m/mnemo-mcp · 2,990 tokens

mcp-python-exec-sandbox CLAUDE.md

Claude Code instructions for lu-zhengda/mcp-python-exec-sandbox, covering claude.md, project, stack, structure and commands.

lu-zhengda/mcp-python-exec-sandbox · 588 tokens