borme-registry-es

borme-registry-es is a skill for Claude Code, Codex from george-kozlitin/borme-mcp. It costs 182 tokens per session (2,588 once invoked), scanned A, original, MIT.

A lookup skill for Spanish companies using the BORME, Spain's official commercial registry gazette. It uses an MCP server to find company notices, history, appointments, departures, tax IDs, and trademarks.

In plain words
What is it for?
Use it to investigate a Spanish company's incorporation, history, management changes, registry events, or trademark and tax-ID records.
Why use it?
It avoids manually searching and interpreting scattered registry notices when checking a Spanish company. The skill says not to answer if its BORME server is unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to investigate a Spanish company's incorporation, history, management changes, registry events, or trademark and tax-ID records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/george-kozlitin/borme-mcp/borme-registry-es
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.

Any agent
npx skills add george-kozlitin/borme-mcp --skill borme-registry-es
Clone the repo
git clone --depth 1 https://github.com/george-kozlitin/borme-mcp

Made for: Claude Code, Codex.

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 borme-registry-es

README.md
[![agentmods](https://agentmods.dev/badge/skills/george-kozlitin/borme-mcp/borme-registry-es/github.svg)](https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry-es)
Your own site
<a href="https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry-es"><img src="https://agentmods.dev/badge/skills/george-kozlitin/borme-mcp/borme-registry-es/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for borme-registry-es

Your own site · 80×15
<a href="https://agentmods.dev/skills/george-kozlitin/borme-mcp/borme-registry-es"><img src="https://agentmods.dev/badge/skills/george-kozlitin/borme-mcp/borme-registry-es.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00182 $0.02588
Opus 5.5 $0.00073 $0.01035
Sonnet 5.5 $0.00036 $0.00518
Haiku 4.5 $0.00018 $0.00259

Measured 20d ago against content hash acd68fad8f9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

borme-registry-es 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 20d 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.

skills/borme-registry-es/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BORME — el Boletín Oficial del Registro Mercantil

El servidor MCP borme contiene los anuncios de sociedades de la sección A del BORME desde 2009, convertidos en eventos tipados, y ofrece además consultas por NIF y por marca. Esta skill indica qué herramienta llamar, cómo encadenarlas y cómo presentar lo que devuelven. La descripción y el esquema de parámetros de cada herramienta explican sus parámetros; léalos también.

Conexión

El endpoint alojado es https://mcp.bormeapi.com/mcp (transporte Streamable HTTP). Funciona sin clave con el plan gratuito. Con clave, envíela en la cabecera X-API-Key:

  • Claude Code: claude mcp add --transport http borme https://mcp.bormeapi.com/mcp --header "X-API-Key: SU_CLAVE"
  • Clientes que se configuran con JSON (el mcp.json de Cursor y similares): {"mcpServers": {"borme": {"url": "https://mcp.bormeapi.com/mcp", "headers": {"X-API-Key": "SU_CLAVE"}}}}

Claves: https://bormeapi.com/es/account. Planes y precios: https://bormeapi.com/es/precios.

Si las herramientas de borme no están disponibles en esta sesión, diga que el servidor MCP de BORME no está conectado, facilite al usuario las líneas anteriores y no responda de memoria.

Qué incluye cada plan

  • Sin clave (free): search_events, company_history y daily_digest sobre los últimos 7 días; list_act_types y registry_stats. 50 llamadas al día por dirección IP.
  • basic: los últimos 365 días, más company_by_nif, brand_owner y company_brands.
  • pro: todo lo de basic, con todo el histórico desde 2009.
  • risk: todo lo de pro, más recent_signals.

Si la respuesta trae plan_window, se aplicó la ventana del plan (company_history lo incluye en todas las respuestas de los planes free y basic). Dígaselo al usuario una vez, en una frase, e indíquele qué cubre el resto: una clave para los últimos 365 días (basic) y pro para todo el histórico. No repita la llamada con fechas anteriores —el servidor las recorta igual— ni tome un resultado vacío como prueba de que antes no pasó nada.

Read the full file on GitHub · 167 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. 20d ago First seen · 167 lines · 182 tokens per session scan A acd68fad8f9d

Subscribe to this mod's changes

borme-registry-es is a skill published in the GitHub repository george-kozlitin/borme-mcp (0 stars, last pushed 20d ago), licensed MIT. It adds 182 tokens to every session and 2,588 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-20.

Related

borme-registry-es compared with skills from other repositories

borme-registry-es next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
borme-registry-esgeorge-kozlitin/borme-mcpSkill020d agoMITA182Claude Code, Codex
fto-triageanthropics/claude-for-legalSkill9.9k2d agoApache-2.0A81Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k2d agoApache-2.0A68Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA49Claude Code
regulatory-research-fallbackHKUDS/OpenSpaceSkill7.9k2d agoMITA20Claude Code, Codex
terms-of-servicegenspark-ai/genofficeSkill12kyesterdayApache-2.0A32Claude Code, Codex
x-scorecardx-cmd/x-cmdSkill4.7k9d agoApache-2.0A57Claude Code, Codex