db-delay-predictor

db-delay-predictor is a skill for Claude Code, Codex from dewalt-1/wheres-my-db. It costs 49 tokens per session (1,940 once invoked), scanned A, original, MIT.

A guide for predicting delays and missed connections on Deutsche Bahn, Germany’s national railway, using train stops, connections, and service disruption notices.

In plain words
What is it for?
Use it to check a named train, assess whether a transfer will hold, find route disruptions, or compare the reliability of travel options.
Why use it?
It gives an earlier, more realistic view than simply reading the printed timetable, especially when delays have not yet appeared there.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to check a named train, assess whether a transfer will hold, find route disruptions, or compare the reliability of travel options.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dewalt-1/wheres-my-db/skill-db-delay
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.

Any agent
npx skills add dewalt-1/wheres-my-db --skill skill-db-delay
Clone the repo
git clone --depth 1 https://github.com/dewalt-1/wheres-my-db

Made for: Claude Code, Codex.

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 db-delay-predictor

README.md
[![agentmods](https://agentmods.dev/badge/skills/dewalt-1/wheres-my-db/skill-db-delay/github.svg)](https://agentmods.dev/skills/dewalt-1/wheres-my-db/skill-db-delay)
Your own site
<a href="https://agentmods.dev/skills/dewalt-1/wheres-my-db/skill-db-delay"><img src="https://agentmods.dev/badge/skills/dewalt-1/wheres-my-db/skill-db-delay/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.

agentmods 80×15 button for db-delay-predictor

Your own site · 80×15
<a href="https://agentmods.dev/skills/dewalt-1/wheres-my-db/skill-db-delay"><img src="https://agentmods.dev/badge/skills/dewalt-1/wheres-my-db/skill-db-delay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,940 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.01940
Opus 5 $0.00024 $0.00970
Sonnet 5 $0.00010 $0.00388
Haiku 4.5 $0.00005 $0.00194

Measured 8d ago against content hash 04a33efa8034, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

db-delay-predictor 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.

packages/skill-db-delay/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deutsche Bahn Delay Predictor

The goal is to give the user a more honest answer than the official DB timetable would: by reading upstream-stop delays, connection chains, and active Störungsmeldungen, predict the delay before the timetable updates.

When to use

  • "Is my ICE 597 on time?"
  • "I'm in Hannover, will I make my 14:32 to Berlin?"
  • "Will my connection in Frankfurt hold if my train is late?"
  • "Are there any disruptions on the Köln–Frankfurt route right now?"
  • "Tomorrow morning Köln → München, which option is most reliable?"

When NOT to use

  • The user wants only the printed timetable, no prediction — use plan_journey and return the data without editorializing.
  • The user asks about ticket prices, seat reservations, refunds, BahnCard — out of scope; say so.

Decision tree — which tool to call first

User mentions a specific train name (ICE 597, RE 9, etc.)
    → get_train_status(name, date?)   (single call returns identifier + full per-stop status + connections)

User describes a route + time ("Hannover → Berlin around 14:30")
    → resolve_station for both endpoints → plan_journey

User mentions a transfer concern ("will I make my connection in Frankfurt?")
    → get_train_status for the incoming train
    → look at outgoingConnections at the transfer station
    → if needed, get_train_status for the connecting train

Ambiguous (e.g. just a station name with no time)
    → ask ONE clarifying question: direction? time? today or tomorrow?

find_train exists as a lightweight variant of get_train_status that returns just the TrainIdentifier — use it when you just need to confirm a train exists or pick a specific operating date among candidates, without paying for the full per-stop fetch.

When resolve_station returns multiple matches with similar names, ask the user to pick — don't guess. "Frankfurt" can be Frankfurt am Main Hbf, Frankfurt (Oder), or FRA Flughafen Fernbahnhof, and the answer changes completely.

Disambiguating line numbers — don't volunteer geography from memory

Read the full file on GitHub · 138 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. 8d ago First seen · 138 lines · 49 tokens per session scan A 04a33efa8034

Subscribe to this mod's changes

db-delay-predictor is a skill published in the GitHub repository dewalt-1/wheres-my-db (0 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,940 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens