Borrowing it
Nothing to install: this file belongs to eric134422/db-fahrplan-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eric134422/db-fahrplan-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/eric134422/db-fahrplan-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/eric134422/db-fahrplan-mcp/agents-md)<a href="https://agentmods.dev/instructions/eric134422/db-fahrplan-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/eric134422/db-fahrplan-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/eric134422/db-fahrplan-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/eric134422/db-fahrplan-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00456 | $0.00456 |
| Opus 5 | $0.00228 | $0.00228 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
db-fahrplan-mcp AGENTS.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 8d 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
Agent guide: presenting DB Fahrplan data
How to display results from this MCP server's tools to the user. This is about output formatting only — tool usage is documented in README.md.
Departure / delay lists → always a table
When showing more than one train, use a Markdown table with these columns:
| Planned | Train | Result |
|---|---|---|
| 17:21 | RE4 (NX 26429) | +27 min |
- Planned: planned local time,
HH:MM. Add the date once above the table, not per row. - Train: line and train label, formatted
LINE (TRAIN), e.g.RE4 (NX 26419). The line (RE4, RB33, S41 …) is what users know — never drop it, even if every row has the same line. If there is nolinefield (e.g. ICE/IC), use the train label alone:ICE 14. - Result: the real-time outcome, one of:
on time— delay_minutes is 0+X min— positive delay; bold at 15 min or more**cancelled**— always bold; if a delay was known before cancellation, append(+X before that)replacement bus— when the train runs asBus NNNN; note a shortened route if the destination differs from the originalno record— no change data available; note the ambiguity: "on time or record aged out"
Single-train answers
Prose, no table. Still use the full designation: "RE4 (NX 26425), planned 15:21, was cancelled."
General rules
- Times in German local time,
HH:MM, no seconds. - Platform changes matter: mention
platform → changed_platformwhen present. - Sort rows by planned time, ascending.
- Don't show raw field names (
delay_minutes,eva) to the user; translate them. - EVA numbers only on request — users think in station names.
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.
- 8d ago First seen · 33 lines · 456 tokens per session scan A ac59d3b19906
db-fahrplan-mcp AGENTS.md is an instructions file published in the GitHub repository eric134422/db-fahrplan-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 456 tokens to every session, about $0.0023 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.