FirstData AGENTS.md

Repository instructions for FirstData, a data-only collection describing authoritative public datasets and other real-world data sources.

In plain words
What is it for?
Use them when adding or editing source records, installing dependencies with uv, or running schema, duplicate-ID, domain, and full repository checks.
Why use it?
They explain that changes are metadata edits rather than application-code changes and provide the checks needed to validate JSON files and identifiers.

Instructions file for CodexOpenCode

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/agents-md
Clone the repo
git clone --depth 1 https://github.com/MLT-OSS/FirstData

Made for: Codex, OpenCode.

Per session 1,716 This file is loaded in full into every session.
When invoked 1,716 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 $0.01716 $0.01716
Opus 5 $0.00858 $0.00858
Sonnet 5 $0.00343 $0.00343
Haiku 4.5 $0.00172 $0.00172

Measured 2d ago against content hash 9c6fd0a220d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FirstData 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 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.

AGENTS.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is intended for AI coding agents (Claude Code, OpenClaw, Codex, Copilot, Cursor, etc.) working in this repository.

What This Repo Is

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.).

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.

The Only Thing You Need to Know: The JSON Schema

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

Required Fields

{
  "id": "worldbank-open-data",
  "name": {
    "en": "World Bank Open Data",
    "zh": "世界银行开放数据"
  },
  "description": {
    "en": "...",
    "zh": "..."
  },
  "website": "https://www.worldbank.org",
  "data_url": "https://data.worldbank.org",
  "api_url": "https://api.worldbank.org/v2/",
  "authority_level": "international",
  "country": null,
  "domains": ["economics", "health", "education"],
  "geographic_scope": "global",
  "update_frequency": "quarterly",
  "tags": ["world bank", "development", "gdp", "poverty", "世界银行"],
  "data_content": {
    "en": ["GDP and national accounts", "Poverty and inequality indicators"],
    "zh": ["GDP和国民账户", "贫困和不平等指标"]
  }
}

Field Rules

Field Allowed Values / Constraints
id Lowercase, hyphens only. Must be globally unique. Pattern:^[a-z0-9-]+$
name.en Required. Add zh and native when applicable
description.en Required. Add zh when applicable
website Top-level org homepage
data_url Must point directly to the data access/download page, NOT the homepage
api_url API docs or endpoint URL. Use null if no API exists
authority_level government · international · research · market · commercial · other
country ISO 3166-1 alpha-2 (e.g."CN", "US"). Must be null when geographic_scope is global or regional
domains Array of strings, at least one. MUST use lowercase (e.g., "economics" not "Economics"). See DOMAINS.md for standard domain list
geographic_scope global · regional · national · subnational
update_frequency real-time · daily · weekly · monthly · quarterly · annual · irregular
tags Mixed Chinese/English keywords for semantic search. Include synonyms and data type names
data_content Optional but recommended. Lists of strings describing what data is available

Read the full file on GitHub · 153 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 · 153 lines · 1,716 tokens per session scan A 9c6fd0a220d9

Subscribe to this mod's changes

FirstData AGENTS.md is an instructions file published in the GitHub repository MLT-OSS/FirstData (182 stars, last pushed 15d ago), licensed MIT. It adds 1,716 tokens to every session, about $0.0086 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.