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.
git 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/rules/frihet-io/frihet-mcp/frihet-fiscal)<a href="https://agentmods.dev/rules/frihet-io/frihet-mcp/frihet-fiscal"><img src="https://agentmods.dev/badge/rules/frihet-io/frihet-mcp/frihet-fiscal/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/rules/frihet-io/frihet-mcp/frihet-fiscal"><img src="https://agentmods.dev/badge/rules/frihet-io/frihet-mcp/frihet-fiscal.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 | $0.00014 | $0.00357 |
| Opus 5 | $0.00007 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
frihet-fiscal 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 9d 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
Apply this when using the Frihet MCP tools for invoicing, expenses or tax.
- VAT (IVA): mainland Spain uses 21% (general), 10% (reduced), 4% (super-reduced). Pick the rate per line item, not per invoice.
- Canary Islands: use IGIC (general 7%), not IVA. Ceuta & Melilla use IPSI. Frihet applies the right zone rate automatically — set the client's region.
- IRPF retención: Spanish freelancers may apply professional withholding (15%, or 7% for newly registered). Do not add it for non-Spanish clients.
- EU B2B: reverse-charge / intra-community supplies need a VAT number validated via VIES (
frihet_tax_id_vies_lookup). Never invent a NIF/CIF/IBAN — ask or look it up. - Compliance is automatic: VeriFactu (state), TicketBAI (Basque Country) and Facturae/FACe (B2G) are handled by Frihet on issue. Don't fabricate fiscal identifiers or submission acks — read the real status with the
verifactu_status/ticketbai_status/face_statustools. - Tax models: Modelo 303 (quarterly IVA), 130 (quarterly IRPF), 390 (annual IVA), 347 (third parties > €3,005). Use the
get_modelo_*_summarytools rather than computing by hand. - Confirm before destructive actions (delete, refund, mark-paid). These mutate real business records.
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.
- 9d ago First seen · 15 lines · 14 tokens per session scan A a1b2371a234d
frihet-fiscal is a cursor rule published in the GitHub repository Frihet-io/frihet-mcp (9 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 357 once invoked, about $0.0001 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 cursor rules, from other repositories
mcp-usage
How to use the AINumbers MCP server (fintech compliance tools and workflows).
typescript-standards
// Good: Typed error handling function loadConfig(): Config { try { // ... loading logic } catch (error) { if (error instanceof yaml.YAMLException) { throw new Error(Invalid YAML in configuration file: ${error.message}); } throw error; } }.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.