ddb-mcp: Skill for Claude Code

.claude/skills/ddb-search/SKILL.md

ddb-search is a skill for Claude Code from nestordemeure/ddb-mcp. It costs 56 tokens per session (3,282 once invoked), scanned A, original, Apache-2.0.

A command-line search tool for the Deutsches Zeitungsportal, Germany’s national online archive of digitised newspapers, especially German-language papers from 1850 to 1950.

In plain words
What is it for?
Use it to research German press coverage, including reports about touring performers. It can search, inspect matches, filter results, and download the archive’s OCR text.
Why use it?
It avoids manually searching millions of scanned newspaper pages and helps locate exact pages, dates, titles, and matching text.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is nestordemeure/ddb-mcp's own configuration. It tells Claude Code how to work on ddb-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ddb-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nestordemeure/ddb-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.

Copy the file
curl -O https://raw.githubusercontent.com/nestordemeure/ddb-mcp/main/.claude/skills/ddb-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nestordemeure/ddb-mcp

Made for: Claude Code.

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 ddb-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/nestordemeure/ddb-mcp/ddb-search/github.svg)](https://agentmods.dev/skills/nestordemeure/ddb-mcp/ddb-search)
Your own site
<a href="https://agentmods.dev/skills/nestordemeure/ddb-mcp/ddb-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/ddb-mcp/ddb-search/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 ddb-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/nestordemeure/ddb-mcp/ddb-search"><img src="https://agentmods.dev/badge/skills/nestordemeure/ddb-mcp/ddb-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,282 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 $0.00056 $0.03282
Opus 5 $0.00028 $0.01641
Sonnet 5 $0.00011 $0.00656
Haiku 4.5 $0.00006 $0.00328

Measured 10d ago against content hash 7146f306f961, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ddb-search 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 10d 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.

.claude/skills/ddb-search/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deutsches Zeitungsportal (DDB)

The national newspaper portal of Germany. It collects the holdings of the Staatsbibliothek zu Berlin, the state and university libraries, and dozens of regional institutions. It holds approximately 33.8 million digitised pages, and approximately 27.9 million of them are from 1850 to 1949. Use it for the German press. The 1920s and the 1930s, the years of the great Weimar mind readers, are the decades with the best coverage in the full collection.

The results are individual pages, not issues and not titles. A result tells you the newspaper, the date and the page number, and it includes the matched text.

Commands

ddb search "<query>" [--pages N|N-M|all] [--rows N] [filters] [--json]
ddb facets <field> ["<query>"] [--limit N] [filters]   # what values a filter can take
ddb snippets <id> "<query>"   # where a query appears inside one page or issue
ddb get <id>                  # download OCR text, prints path to the cached file

The filters for search and facets are --from-year, --to-year, --title TEXT (the newspaper title), --place TEXT, --language CODE (ISO 639-2, ger), --provider TEXT (the institution that holds the item) and --zdb-id ID.

There is no --sort option. The results come back in order of relevance. See the risks below.

facets — how to find a value, and how to describe a result set

ddb facets place|provider|language|title lists the values that a filter can take, with page counts, and it puts the largest counts first. It does two different tasks.

How to find the correct value. --place and --provider match a full string, and a near-miss is not a near-miss. It is silence. --place Halle reports 0 pages matched with no error. --place "Halle (Saale)" matches 1.1 million pages. --provider Bayerische matches nothing. --provider "Bayerische Staatsbibliothek" matches 8.3 million. You cannot guess which form the index holds, so look before you filter. --title is the one exception: it is analysed text with German stemming, so a fragment of a title operates correctly.

Read the full file on GitHub · 120 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. 10d ago First seen · 120 lines · 56 tokens per session scan A 7146f306f961

Subscribe to this mod's changes

ddb-search is a skill published in the GitHub repository nestordemeure/ddb-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 3,282 once invoked, about $0.0003 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

frontmcp-development

Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…

agentfront/frontmcp · 196 tokens

pipefy-ai-agents

Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…

pipefy/ai-toolkit · 84 tokens

html-portal-generator

Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.

athola/skrills · 40 tokens

pipefy-automations

Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.

pipefy/ai-toolkit · 60 tokens

pipefy-portal-setup

Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Covers 20 MCP tools on Interfaces + internalapi. Not for pipes/cards.

pipefy/ai-toolkit · 57 tokens

pipefy-introspection

Use this skill when you need to discover GraphQL type shapes, mutation signatures, enum values, or execute arbitrary GraphQL as a fallback. This is the first fallback tier (Tier 2) when dedicated MCP tools fail or don't exist for an operation. 7 MCP tools.

pipefy/ai-toolkit · 61 tokens