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/volsch/md24de-mcp/copilot-instructionsgit clone --depth 1 https://github.com/volsch/md24de-mcpWrote 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/volsch/md24de-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/volsch/md24de-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/volsch/md24de-mcp/copilot-instructions.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 | $0.00708 | $0.00708 |
| Opus 5 | $0.00354 | $0.00354 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
md24de-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
md24de-mcp — Copilot Instructions
Project overview
Unofficial MCP (Model Context Protocol) server that wraps the python-md24de library to expose messdienst24.de utility-consumption data as MCP tools.
Language & runtime
- Python 3.12+; use syntax compatible with Python 3.12 and above
- All files start with
from __future__ import annotations
Code style
- Formatter/linter: ruff (
line-length = 100, targetpy312) - Active ruff rules:
E, F, I, N, W, UP, ANN, S, B, C4, PIE, RET, SIM— all annotations required (ANN) - Type checker: pyright strict — every function must be fully annotated; no
Anyunless unavoidable - Private module files are prefixed with
_(e.g._cache.py,_config.py) - Public surface is re-exported from
__init__.pyonly; internals stay in_*.pymodules
MCP server
- MCP framework: FastMCP (
from mcp.server.fastmcp import FastMCP) - The server instance, all tools, and all resources live in
server.py - Config and caches are initialised lazily on the first tool call — never at import time
- Each tool call creates a fresh
Md24deClient, performs the minimum required requests, then closes the connection - Results are cached in memory via
Cache[T]from_cache.py
Configuration
Runtime config is loaded from environment variables:
MD24DE_TENANT,MD24DE_USERNAME,MD24DE_PASSWORD(required) — loaded in_config.pyMD24DE_TIMEOUT(optional, default 30 s),MD24DE_CACHE_TTL(optional, default 1800 s) — loaded in_config.pyLOG_LEVEL(optional, defaultWARNING) — applied inmain()in__init__.py
Models
- All data models are
@dataclass(frozen=True)where applicable - Use Python 3.12+ type parameter syntax (
class Foo[T]:) instead ofGeneric[T]
Logging
- Every
_*.pymodule has_log = logging.getLogger(__name__)at module level __init__.pyregisterslogging.NullHandler()on themd24de_mcproot loggermain()in__init__.pyappliesLOG_LEVELenv var vialogging.basicConfig()and propagates it to themd24deandhttpxloggers- Use
_log.debug(...)for operational events (cache hits/misses, byte counts, month/year values) - Never log credentials (username, password)
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 · 61 lines · 708 tokens per session scan A bc17919dc596
md24de-mcp copilot-instructions.md is an instructions file published in the GitHub repository volsch/md24de-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 708 tokens to every session, about $0.0035 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 instructions, from other repositories
aemo-mcp CLAUDE.md
Claude Code instructions for Bigred97/aemo-mcp, covering aemo-mcp, source, curated datasets (10), repo-specific module set and repo-specific gotchas.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.