businesscentral

businesscentral is a skill for Claude Code from enzoleonardi/claude-businesscentral-skill. It costs 41 tokens per session (3,623 once invoked), scanned A, original, MIT.

A skill for working with Microsoft Dynamics 365 Business Central, an online business system for managing records such as customers, orders, invoices, vendors, and products. It uses Business Central's REST API, a web interface for programmatic access.

In plain words
What is it for?
Use it to authenticate and query Business Central, or create, update, and delete customers, sales orders, invoices, vendors, and items.
Why use it?
It lets an agent manage Business Central data through commands instead of manually performing every operation in the web application.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the businesscentral plugin — 1 skill shipped together

Good fit Use it to authenticate and query Business Central, or create, update, and delete customers, sales orders, invoices, vendors, and items.

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

Made for: Claude Code.

Or install businesscentral, the plugin that ships this one along with the rest of its 1 skill.

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 businesscentral

README.md
[![agentmods](https://agentmods.dev/badge/skills/enzoleonardi/claude-businesscentral-skill/businesscentral/github.svg)](https://agentmods.dev/skills/enzoleonardi/claude-businesscentral-skill/businesscentral)
Your own site
<a href="https://agentmods.dev/skills/enzoleonardi/claude-businesscentral-skill/businesscentral"><img src="https://agentmods.dev/badge/skills/enzoleonardi/claude-businesscentral-skill/businesscentral/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 businesscentral

Your own site · 80×15
<a href="https://agentmods.dev/skills/enzoleonardi/claude-businesscentral-skill/businesscentral"><img src="https://agentmods.dev/badge/skills/enzoleonardi/claude-businesscentral-skill/businesscentral.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,623 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 $0.00041 $0.03623
Opus 5 $0.00020 $0.01811
Sonnet 5 $0.00008 $0.00725
Haiku 4.5 $0.00004 $0.00362

Measured 12d ago against content hash 78ee08fe73d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

businesscentral 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 12d 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.

Node.js `fetch()` also doesn't work in the sandbox — use `curl` directly for token exchange.
skills/businesscentral/SKILL.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Business Central Skill for Claude Code

Interact with Microsoft Dynamics 365 Business Central via the REST API using bc-cli.

Prerequisites

  1. Node.js 18+ installed
  2. bc-cli installed from this skill's directory:
    # From skill directory
    npm link
    # Or run directly
    node <skill-path>/bin/bc-cli.mjs <command>
    

No Azure AD setup needed — a default app registration is included.

Binary location: bc-cli is at ../../bin/bc-cli.mjs relative to this SKILL.md file. In Cowork, find it at <plugin-path>/bin/bc-cli.mjs.

Authentication

Step 1: Check if already authenticated

bc-cli status

If status shows "Active", you're ready — skip to "Operation Safety Levels".

Step 2: Login

Claude Code (local machine — no sandbox)

Just run:

bc-cli login

This will:

  1. Open your browser to the Microsoft login page
  2. You sign in with your Microsoft/Business Central account
  3. Token is saved automatically with auto-refresh
  4. Tenant and environment are auto-detected

That's it. No Client ID, no Tenant ID, no environment to configure — everything is automatic.

Claude Cowork (sandboxed environment)

IMPORTANT — Domain allowlist setup (MUST do before anything else):

The user MUST add these domains to the Cowork network allowlist:

  • *.microsoftonline.com (Microsoft authentication)
  • *.businesscentral.dynamics.com (Business Central API)

How: In Cowork, go to Settings > Capabilities > Domain allowlist > Additional allowed domains and add both domains. Without this, all API calls will fail.

In Cowork, bc-cli login cannot open the user's browser because the sandbox is isolated. Node.js fetch() also doesn't work in the sandbox — use curl directly for token exchange.

Step A — Generate the auth URL:

bc-cli login-url --port=33333

This outputs JSON with authorizeUrl, verifier, and redirectUri. Save the verifier — you'll need it in Step C.

Step B — Ask the user to authenticate:

Read the full file on GitHub · 444 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. 12d ago First seen · 444 lines · 41 tokens per session scan A 78ee08fe73d6

Subscribe to this mod's changes

businesscentral is a skill published in the GitHub repository enzoleonardi/claude-businesscentral-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 3,623 once invoked, about $0.0002 per session on Opus 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

payment-advisor

Recommends the single best payment provider for the user's project after a short interactive wizard, then hands off to the implementer. Runs a deterministic local ranking engine instead of scoring by hand, so the same situation always yields the same answer and every rejection has an exact reason. Computes real fees…

Hainrixz/agente-pagokit · 114 tokens

laravel-stripe-connect

Use when implementing multi-vendor marketplace payments, seller onboarding, commissions, payouts, or split payments with Stripe Connect.

fusengine/agents · 29 tokens

paypal-best-practices

PayPal integration guidance, code examples, and best practices. Use for checkout, card fields, BNPL, Pay Later, Venmo, subscriptions, invoicing, disputes, payouts, webhooks, APMs, JS SDK v5, JS SDK v6, createInstance, payment sessions, web components, Fastlane, payment links, donations, 3D Secure, vaulting, iDEAL…

paypal/AI-Toolkit · 107 tokens

stripe-best-practices

Guides Stripe integration decisions — API selection (Checkout Sessions vs PaymentIntents), Connect platform setup (Accounts v2, controller properties), billing/subscriptions, Treasury financial accounts, integration surfaces (Checkout, Payment Element), migrating from deprecated Stripe APIs, and security best…

biggora/dev-team · 111 tokens

stripe

Integrate and manage Stripe payment processing — accept payments, manage subscriptions, generate invoices, handle refunds, and configure webhooks. Covers Stripe Checkout, Payment Intents, Subscriptions, Invoicing, and Connect. Context: User wants to set up Stripe user: "integrate Stripe payments into my app" Context…

lukaskellerstein/claude-my-marketplace · 191 tokens

ecommerce-assumptions

Resolves all financial model drivers for a pre-launch ecommerce business from founder intake data. Maps qualitative inputs (order volume bands, margin bands, difficulty levels) to specific numeric values using curated industry benchmarks across 11 product categories and 5 regions. Calculates derived values including…

aivant-io/bizplan-plugin · 89 tokens