agentmods.dev

mcp-csu CLAUDE.md

mcp-csu CLAUDE.md is an instructions file for coding agents from reloadcz/mcp-csu. It costs 1,484 tokens per session, scanned A, original, MIT.

A set of instructions for agents using mcp-csu, a server that retrieves data from the Czech Statistical Office’s DataStat API. The API provides official Czech statistics in datasets and predefined tables.

In plain words
What is it for?
Searching Czech statistical datasets, checking indicators and dimensions, selecting years or regions, and downloading table data as CSV.
Why use it?
It explains which tools to use for finding datasets, understanding their structure, and retrieving data, along with the server’s operating rules.

Instructions file

not rated 2 +1 6mo ago A scan 1,484 tokens original MIT
View the source file reloadcz/mcp-csu
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/reloadcz/mcp-csu/claude-md
Clone the repo
git clone --depth 1 https://github.com/reloadcz/mcp-csu

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-csu CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/reloadcz/mcp-csu/claude-md.svg)](https://agentmods.dev/instructions/reloadcz/mcp-csu/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/reloadcz/mcp-csu/claude-md"><img src="https://agentmods.dev/badge/instructions/reloadcz/mcp-csu/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,484 This file is loaded in full into every session.
When invoked 1,484 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 5.1 $0.01484 $0.01484
Opus 5 $0.00742 $0.00742
Sonnet 5 $0.00297 $0.00297
Haiku 4.5 $0.00148 $0.00148

Measured 5d ago against content hash 908cd8ae886d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-csu CLAUDE.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.

CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-csu

MCP server for the Czech Statistical Office (ČSÚ) DataStat API. Single-file Python server (mcp_csu/server.py), runs via uvx mcp-csu.

For AI agents using this MCP server

Quick start

search_datasets("obyvatelstvo")  →  find dataset code
get_dataset("OBY01")             →  see dimensions + indicators
get_dataset_selections("OBY01")  →  find predefined table code
get_selection_data("OBY01T01")   →  get CSV data

Tool overview

Find data:

  • search_datasets(query) — full-text search across 700+ datasets
  • search_selections(query) — full-text search across 1500+ predefined tables
  • list_datasets(offset, limit) — browse all datasets
  • list_selections(offset, limit) — browse all predefined tables

Understand structure:

  • get_dataset(code) — dimensions, indicators, keywords, update frequency
  • get_dataset_selections(code) — predefined tables for a dataset
  • get_dimension_items(code, level) — possible values (years, regions, categories)
  • get_indicator(code) — indicator definition

Get data:

  • get_selection_data(code, max_rows) — primary tool, fetches CSV from a predefined table
  • get_value(dataset, indicator, dim_codes, item_codes) — single precise value
  • custom_query(...) — advanced, arbitrary dataset query
  • get_dataset_metadata(code, version) — record count, time range, last update

Critical rules

  1. Always search in Czech. The database is Czech-language. Use the vocabulary below.
  2. Prefer get_selection_data over custom_query. Selections are reliable and pre-configured. custom_query is fragile with hierarchical dimensions.
  3. Start with search, not list. search_datasets and search_selections are faster and more targeted than browsing.
  4. Inspect before querying. Always call get_dataset() before get_value() or custom_query() to learn dimension codes and indicator codes.
  5. Respect max_rows. Default is 100. Increase only when the user needs more. Set to 0 only if explicitly asked for all data.

Read the full file on GitHub · 139 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. 5d ago First seen · 139 lines · 1,484 tokens per session scan A 908cd8ae886d

Subscribe to this mod's changes

mcp-csu CLAUDE.md is an instructions file published in the GitHub repository reloadcz/mcp-csu (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 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.

Research
Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens