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 skills add Frihet-io/frihet-mcp --skill gastosgit clone --depth 1 https://github.com/Frihet-io/frihet-mcpWrote 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/skills/frihet-io/frihet-mcp/gastos)<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/gastos"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/gastos/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.
<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/gastos"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/gastos.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.00384 |
| Opus 5.5 | $0.00018 | $0.00154 |
| Sonnet 5.5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
gastos 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 3d 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.
What it actually says
Gastos y proveedores
Lee las reglas de Frihet antes de actuar.
Para revisar, resuelve periodo y empresa, recorre list_expenses y consulta
get_expense cuando falte detalle. Agrupa por categoría, proveedor y moneda
comprobada. Muestra justificantes o datos pendientes y posibles duplicados con
sus IDs; dos registros parecidos no son prueba suficiente para borrar uno.
Para registrar un gasto autorizado, confirma descripción, importe en la unidad del esquema, fecha y proveedor. Busca coincidencias antes de crearlo. No des por deducible un gasto, inventes una fecha de pago ni marques como pagado algo que solo se ha registrado. Si falta tratamiento fiscal, deja esa decisión pendiente; el valor por defecto de un campo no prueba que sea correcto.
Usa create_expense o update_expense solo para los cambios concretos pedidos.
Revisa sus efectos configurados: incluso un alta puede disparar webhooks.
Lee el resultado con get_expense y devuelve el ID, los campos guardados y lo
pendiente. Si el resultado es incierto, consulta antes de repetir.
list_vendors, get_vendor, create_vendor y update_vendor permiten gestionar
proveedores con la misma comprobación de identidad y alcance. No atribuyas OCR,
carga de adjuntos, borrado de gastos ni transferencias a este flujo: esas
capacidades no se deducen de las herramientas anteriores.
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.
- 3d ago First seen · 34 lines · 45 tokens per session scan A 478f35acace2
gastos is a skill published in the GitHub repository Frihet-io/frihet-mcp (12 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 384 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
escalation
Escalate a disputed refund to the billing lead.
expense-report
Generate a detailed expense breakdown by category for a given period. Use when the user asks for an expense report, spending summary, Ausgabenübersicht, cost analysis, or wants to understand where their money is going.
refunds
Process customer refunds.
create-invoice
Create and optionally send a new invoice to a client. Use when the user wants to invoice someone, bill a client, or create a new Rechnung or faktura.
corporate-tax-registration
Prepare the corporate tax registration (Fragebogen zur steuerlichen Erfassung for a GmbH/UG) through a guided chat. Use when a newly founded GmbH/UG needs its Steuernummer, the user asks what to do after the notary appointment, or wants to register the company with the Finanzamt. Final submission happens in the Norman…
monthly-reconciliation
Perform a complete monthly financial reconciliation - review all transactions, match invoices, check outstanding payments, and prepare for tax filing. Use when the user wants to close the month, do monthly bookkeeping, or perform a Monatsabschluss (zamknięcie miesiąca).