FirstData CLAUDE.md

Repository instructions for FirstData, a data-only collection describing reliable public data sources for AI agents. It explains the project structure, dependency setup, and validation commands.

In plain words
What is it for?
Adding or changing descriptions of government, international, academic, and other open-data sources, then checking the files with the project's validation tools.
Why use it?
They help contributors edit source metadata correctly and catch invalid JSON, duplicate IDs, or inconsistent domain names before submission.

Instructions file

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/mlt-oss/firstdata/claude-md
Clone the repo
git clone --depth 1 https://github.com/MLT-OSS/FirstData
Per session 1,912 This file is loaded in full into every session.
When invoked 1,912 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 $0.01912 $0.01912
Opus 5 $0.00956 $0.00956
Sonnet 5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured 2d ago against content hash 77a94b07893a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FirstData 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 2d 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 · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

FirstData is the External Facts Context Layer for AI Agents — a structured, authoritative collection of global open data sources. It is a pure data repository — no application code, no runtime logic.

Your job here is to create or edit JSON metadata files that describe real-world data sources (government databases, international organizations, academic datasets, etc.).

The project exposes a hosted MCP Server at https://firstdata.deepminer.com.cn/mcp.

Validation

Dependencies are managed with uv. Run the following before submitting:

# Install dependencies (first time only)
uv sync

# Run all validation checks
make check

# Or run checks individually:
make validate       # Validate JSON schema compliance
make check-ids      # Check for duplicate IDs
make check-domains  # Check domain naming consistency

A GitHub Action runs these checks automatically on every PR. PRs that fail validation cannot be merged.

Repository Structure

firstdata/
├── schemas/datasource-schema.json   # JSON Schema v2.0.0 (the source of truth for data format)
├── sources/                         # Individual data source JSON files, organized by category
│   ├── china/                       # Chinese government & institutions
│   ├── international/               # International organizations (by domain)
│   ├── countries/                   # National official sources (by continent/country)
│   ├── academic/                    # Academic research databases (by discipline)
│   └── sectors/                     # Industry sources (by ISIC Rev.4 code)
└── indexes/                         # Auto-generated aggregated indexes (do not edit manually)
    ├── all-sources.json
    ├── by-authority.json
    ├── by-domain.json
    ├── by-region.json
    └── statistics.json

The JSON Schema

Every file under firstdata/sources/ must conform to firstdata/schemas/datasource-schema.json.

Read the full file on GitHub · 174 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. 2d ago First seen · 174 lines · 1,912 tokens per session scan A 77a94b07893a

Subscribe to this mod's changes

FirstData CLAUDE.md is an instructions file published in the GitHub repository MLT-OSS/FirstData (182 stars, last pushed 15d ago), licensed MIT. It adds 1,912 tokens to every session, about $0.0096 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 2026-08-30.