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/aplaceforallmystuff/spain-ai-kit/agents-mdgit clone --depth 1 https://github.com/aplaceforallmystuff/spain-ai-kitWrote 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/aplaceforallmystuff/spain-ai-kit/agents-md)<a href="https://agentmods.dev/instructions/aplaceforallmystuff/spain-ai-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/aplaceforallmystuff/spain-ai-kit/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 | $0.00818 | $0.00818 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
spain-ai-kit 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 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spain AI Kit
MCP servers connecting AI applications to Spanish government open data and legal infrastructure.
What This Is
A TypeScript monorepo (Nx + npm workspaces) providing MCP servers for Spanish government APIs. Inspired by estonia-ai-kit.
Spanish Service Mapping
| Spanish Service | API | Auth | Status |
|---|---|---|---|
| INE (Instituto Nacional de Estadística) | JSON-stat at servicios.ine.es/wstempus/js |
No | Shipped |
| BOE (Boletín Oficial del Estado) | XML at boe.es/datosabiertos/api |
No | Shipped |
| Catastro (Dirección General del Catastro) | SOAP/REST at ovc.catastro.meh.es |
No | Shipped |
| AEMET (Agencia Estatal de Meteorología) | REST at opendata.aemet.es/opendata |
Free API key | Shipped |
| AEAT (Agencia Tributaria) | cl@ve authentication | Yes | Future |
| datos.gob.es | CKAN catalog at datos.gob.es/apidata |
No | Future |
API Endpoints
INE (JSON-stat API)
- Base:
https://servicios.ine.es/wstempus/js/ES/ - Operations: list by theme, search, get series data
- Format: JSON-stat 2.0
- No auth, no rate limit documented
BOE (Open Data API)
- Base:
https://www.boe.es/datosabiertos/api/ - Operations: search by date/keyword, get document, list summaries
- Format: XML
- No auth required
Catastro (OVC Web Services)
- Callejero base:
https://ovc.catastro.meh.es/ovcservweb/OVCSWLocalizacionRC/OVCCallejeroCodigos.asmx/ - Coordenadas base:
https://ovc.catastro.meh.es/ovcservweb/OVCSWLocalizacionRC/OVCCoordenadas.asmx/ - Operations: province/municipality/street lookup, property data by cadastral ref, geocoding, reverse geocoding
- Format: XML (SOAP endpoints, callable via HTTP GET)
- No auth required
AEMET (OpenData API)
- Base:
https://opendata.aemet.es/opendata/ - Auth: API key via
AEMET_API_KEYenv var (free signup at opendata.aemet.es) - Double-call pattern: first call returns envelope with temporary
datosURL, second call fetches actual data - Operations: municipal forecasts (daily/hourly), observations, alerts, UV index, fire risk, beach conditions
- Format: JSON
- Uses
AEMETClient(extends BaseAPIClient) in shared package
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.
- 5d ago First seen · 70 lines · 818 tokens per session scan A 29c7cc352d43
spain-ai-kit AGENTS.md is an instructions file published in the GitHub repository aplaceforallmystuff/spain-ai-kit (7 stars, last pushed 24d ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
l4-ide AGENTS.md
AGENTS.md instructions for smucclaw/l4-ide, covering agents.md, about l4, repository structure, haskell (cabal) and typescript (npm workspaces + turborepo).
uk-legal-mcp CLAUDE.md
Claude Code instructions for paulieb89/uk-legal-mcp, covering claude.md — uk-legal-mcp, what this is, client ecosystems served, documentation index and commands.
uk-due-diligence-mcp AGENTS.md
Instructions for paulieb89/uk-due-diligence-mcp, covering agents.md — uk-due-diligence-mcp, repo shape, deploy, version bump and standard routes (must always be present).
congressgov-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/congressgov-mcp-server, covering agent protocol, what's next?, config, core rules and mcp surface.
decision-anchor-sdk AGENTS.md
AGENTS.md instructions for zse4321/decision-anchor-sdk, covering decision anchor: document for agents, why this environment exists, when da matters, getting started and try it now.
mcp-custos CLAUDE.md
Instructions for an0malous/mcp-custos, covering claude.md — agent guide, project context, spec flow (human-approved gates), conventions and commands.