multi-nif

multi-nif is a skill for Claude Code from beel-es/claude-plugins. It costs 92 tokens per session (2,412 once invoked), scanned A, original, MIT.

An integration guide for BeeL accounts that manage several Spanish tax identities, called NIFs or CIFs. Each company has separate invoices, customers, products, and invoice series, while members or agencies can receive limited access.

In plain words
What is it for?
Use it when requests must target a particular company, when users need company-specific permissions, or when an agency invoices on behalf of managed businesses.
Why use it?
It prevents billing data from being assigned to the wrong company when one API key manages several businesses. It also clarifies access for employees, agencies, accountants, and fleet operators.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the beel-api plugin — 6 skills, 1 MCP server shipped together

Good fit Use it when requests must target a particular company, when users need company-specific permissions, or when an agency invoices on behalf of managed businesses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/beel-es/claude-plugins/multi-nif
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 beel-es/claude-plugins --skill multi-nif
Clone the repo
git clone --depth 1 https://github.com/beel-es/claude-plugins

Made for: Claude Code.

Or install beel-api, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

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 multi-nif

README.md
[![agentmods](https://agentmods.dev/badge/skills/beel-es/claude-plugins/multi-nif/github.svg)](https://agentmods.dev/skills/beel-es/claude-plugins/multi-nif)
Your own site
<a href="https://agentmods.dev/skills/beel-es/claude-plugins/multi-nif"><img src="https://agentmods.dev/badge/skills/beel-es/claude-plugins/multi-nif/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 multi-nif

Your own site · 80×15
<a href="https://agentmods.dev/skills/beel-es/claude-plugins/multi-nif"><img src="https://agentmods.dev/badge/skills/beel-es/claude-plugins/multi-nif.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00092 $0.02412
Opus 5.5 $0.00037 $0.00965
Sonnet 5.5 $0.00018 $0.00482
Haiku 4.5 $0.00009 $0.00241

Measured 1mo ago against content hash fdc2479e1d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

multi-nif scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://app.beel.es/api/v1/companies/550e8400-e29b-41d4-a716-446655440000/invoices \
plugins/beel-api/skills/multi-nif/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BeeL Multi-NIF — Integration Guide

BeeL's multi-NIF model lets one account (one API key) hold many companies, each a Spanish tax ID (NIF/CIF) with its own fully isolated invoices, customers, products and series. Built for professionals with several NIFs, agencies (gestorías) and fleets that invoice on behalf of the businesses they manage.

The golden rules in the beel-api skill apply throughout — especially: never invent endpoints, fields or scopes; verify against the live docs.

The model (know this before writing code)

Concept What it is
Account The tenant you authenticate as. One API key = one account. Owns billing/auth and holds 1..N companies.
Company One fiscal identity (NIF/CIF). Isolated space: its own invoices, customers, products, series — per environment (TEST/PROD).
Member A person with access to the account. Account role OWNER/ADMIN (reach every company) or MEMBER (only companies granted to it, at access level VIEW or OPERATE).
Managed account Another account a provisioner (agency/fleet) creates and operates on behalf of its holder, at an access level it controls: NONE, VIEW or OPERATE.

access_level is one single vocabulary — NONE (no visibility), VIEW (read-only), OPERATE (read and write) — used both for a member's grant over a company and for a provisioner's access over a managed account. It never decides who pays: billing follows the provisioning relationship, not the access level.

Members vs managed accounts — pick the right one

Both give access to operate a business, but point in opposite directions. Don't require both scopes — an integration uses one model:

  • Members (members:*) — a person joins an account that already exists. The owner, billing and NIF stay with that account; the invitee only needs a login (not an account of their own) and does no fiscal onboarding. Use when the client signed up and pays themselves and invites you in.
  • Managed accounts (accounts:write) — you create and run a third party's account (its own NIF, its own billing) and they can later claim it. Use when you onboard them by API and you pay (fleets, mass onboarding, platform gestorías whose clients aren't on BeeL yet).

Read the full file on GitHub · 183 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. 1mo ago Changed · +21 lines fdc2479e1d76
  2. 1mo ago First seen · 162 lines · 92 tokens per session scan A 2696da59300c

Subscribe to this mod's changes

multi-nif is a skill published in the GitHub repository beel-es/claude-plugins (4 stars, last pushed 11d ago), licensed MIT. It adds 92 tokens to every session and 2,412 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

liter-llm-running-the-proxy

Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.

xberg-io/liter-llm · 45 tokens

payment-integration

Stripe, RevenueCat, subscription billing, webhooks, PCI compliance, and tax. Use when integrating payments or subscriptions, handling payment webhooks, or reviewing billing and PCI scope.

travisjneuman/.claude · 40 tokens

bitcoin-infrastructure-electrs

Electrs: Roman Zeyde's Electrum-protocol indexer in Rust. Lightweight, serves Electrum clients; BIP157 filter scan stays on Bitcoin Core. USE WHEN: deploying personal Electrum server, integrating LN with Electrum backend, evaluating indexers.

claude-dev-suite/claude-dev-suite · 62 tokens

bitcoin-infrastructure-esplora

Esplora: Blockstream's HTTP-based block explorer + indexer. REST API at /api/ . Powers blockstream.info, mempool.space's earlier versions, and self-hosted explorers. USE WHEN: deploying a personal block explorer, integrating with Esplora REST API, building wallet / monitoring on Esplora-style endpoint.

claude-dev-suite/claude-dev-suite · 81 tokens

bitcoin-infrastructure-fulcrum

Fulcrum: Calin Culianu's Electrum-protocol indexer in C++. Faster than electrs for high-volume queries. Serves Electrum clients + LN nodes. USE WHEN: deploying high-load Electrum server, comparing with electrs.

claude-dev-suite/claude-dev-suite · 62 tokens

regtech-expert

Expert in regulatory technology, compliance automation, KYC/AML, transaction monitoring, risk assessment, and automated reporting. Use when the user mentions compliance, KYC, AML, transaction monitoring, risk assessment, or regulatory reporting, or when the task involves KYC/AML Compliance, KYC/AML Program, Regulatory…

personamanagmentlayer/pcl · 73 tokens