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.
npx agentmods add instructions/datenoio/internacia-db/agents-mdgit clone --depth 1 https://github.com/datenoio/internacia-dbWrote 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.
[](https://agentmods.dev/instructions/datenoio/internacia-db/agents-md)<a href="https://agentmods.dev/instructions/datenoio/internacia-db/agents-md"><img src="https://agentmods.dev/badge/instructions/datenoio/internacia-db/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01278 | $0.01278 |
| Opus 5 | $0.00639 | $0.00639 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
internacia-db 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internacia DB — AI agent guide
Structured reference data: 256 countries, 1037 intblocks (organizations/groups), 78 blocktypes. Part of the Dateno open-source project. Licensed CC-BY-4.0 (data and documentation); code is MIT.
中文指南：AGENTS.zh.md · llms.zh.txt
What do you need?
| Goal | Start here | Do not |
|---|---|---|
| Query, join, or enrich downstream data | llms.txt → docs/ai-consumers.md | Parse source YAML under data/countries/ or data/intblocks/ |
| Look up countries, borders, org membership | docs/agents/query.md | Join intblocks on includes[].name (use includes[].id) |
| Edit country or intblock YAML | docs/agents/contribute.md | Hand-edit data/datasets/ (generated only) |
| Schema change, new capability, breaking export | docs/agents/openspec-quickstart.md → openspec/AGENTS.md | Implement before approval |
Preferred data access
- DuckDB:
data/datasets/internacia.duckdb(tables:countries,intblocks,blocktypes,memberships,_meta) - Parquet:
data/datasets/{countries,intblocks,blocktypes,memberships}.parquet - Remote: internacia-python (SDK). internacia-api is self-host only — no public hosted HTTP API.
Check version before upgrading: SELECT dataset, version, schema_hash FROM _meta; or read data/datasets/*.manifest.json.
Join keys and gotchas
- Countries:
code(alpha-2, primary),iso3code,wikidata_id - Intblocks:
id(uppercase, e.g.NATO,EU); membership viaincludes[].id→ countrycode bordersuses alpha-3, not alpha-2 — join oniso3codepopulation/area/giniare structs — use.valuefor the number;yearis null when unknown (never 0)- Current ISO countries only (249):
code_status = 'official_iso3166_1' - Intblock id renames: consult
data/datasets/intblocks_aliases.json
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.
- 4d ago First seen · 89 lines · 1,278 tokens per session scan A fd4be9a28e5c
internacia-db AGENTS.md is an instructions file published in the GitHub repository datenoio/internacia-db (11 stars, last pushed 2d ago), licensed MIT. It adds 1,278 tokens to every session, about $0.0064 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.
Other instructions, from other repositories
scalar AGENTS.md
AGENTS.md instructions for scalar/scalar, covering agents.md - ai agent guide for scalar, project overview, prerequisites, first-time setup and commands.
spiceai copilot-instructions.md
Copilot instructions for spiceai/spiceai, covering spice.ai agent instructions, data correctness — absolute top priority, evidence — no claim without a reproduction, build, test, lint (expensive — read first) and git & prs.
moosestack copilot-instructions.md
Instructions for 514-labs/moosestack, covering moose repository guide, code standards, required before each commit, development flow and repository structure.
gem-dota CLAUDE.md
Claude Code instructions for whanyu1212/gem-dota, covering claude.md, commands, install project + dev dependencies, run all tests, including slow/integration markers and run a single test file.
quant-mind CLAUDE.md
Instructions for LLMQuant/quant-mind: CLAUDE.md imports AGENTS.md as the single source of repository instructions for coding agents. Do not duplicate rules here — edit AGENTS.md. Add Claude Code- specific guidance (if any) below the import. This block-level HTML comment is stripped from Claude's context at load, so it…
moosestack AGENTS.md
Instructions for 514-labs/moosestack, covering agents.md, build & development commands, all languages, rust and typescript.