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 norman-finance/norman-mcp-server --skill suggest-categorygit clone --depth 1 https://github.com/norman-finance/norman-mcp-serverWrote 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/norman-finance/norman-mcp-server/suggest-category)<a href="https://agentmods.dev/skills/norman-finance/norman-mcp-server/suggest-category"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/suggest-category/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/norman-finance/norman-mcp-server/suggest-category"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/suggest-category.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00841 |
| Opus 5 | $0.00036 | $0.00420 |
| Sonnet 5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
suggest-category 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help the user find the correct SKR chart of accounts category.
IMPORTANT: SME accounts only. This skill applies to GmbH/UG companies that use DATEV standard chart of accounts (SKR03/SKR04). For freelance accounts, use categorize_transaction instead — it has its own category set and AI detection.
How to determine account type
Call get_company_details and check the isSme field:
isSme: true→ Use this skill (SKR tools below)isSme: false→ Usecategorize_transactionfor freelance AI categorization
Workflow
-
Determine the search approach based on what the user provides:
- If they provide an account number or prefix (digits like
42,4200,6300), usesearch_skr_by_codefor instant CSV-based results. - If they describe a category by name or purpose (e.g. "office rent", "Reisekosten", "software subscriptions"), use
suggest_skr_categorywhich leverages OpenAI to semantically match against the full catalog.
- If they provide an account number or prefix (digits like
-
Show results clearly: Present the matches with:
- Account number (code)
- German name (
nameDe) - English name (
nameEn) - Let the user pick the best fit.
-
Check the company's existing categories: Call
list_company_categoriesto see if the desired category is already provisioned. If it is, inform the user — no need to create a new one. -
Create the category if needed: If the user wants to add it, use
create_company_categorywith:- The account code from the SKR catalog
- The name (use the language the user prefers)
- The cashflow type (INCOME or EXPENSE)
- Optional German name and description
-
Context: The company's active chart of accounts (SKR03 or SKR04) determines which catalog is searched. You can check the current template via
get_company_details.
Tool summary
| Tool | For | What it does |
|---|---|---|
search_skr_by_code |
SME only | Fast CSV lookup by account number prefix |
suggest_skr_category |
SME only | AI (OpenAI) semantic search by name/description |
create_company_category |
SME only | Create a new custom DATEV category |
list_company_categories |
SME only | List categories already provisioned for the company |
categorize_transaction |
All accounts | AI detection for a specific transaction (freelance + SME) |
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.
- 12d ago First seen · 62 lines · 72 tokens per session scan A 00459bf18324
suggest-category is a skill published in the GitHub repository norman-finance/norman-mcp-server (54 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 841 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
bukio-cli
Drive bukio-cli — agent-first double-entry bookkeeping for SMEs across eleven jurisdictions. Book invoices, archive the originals, keep the books balanced.
QuickBooks Automation
Automate QuickBooks accounting workflows including invoicing, expenses, reporting, and bank reconciliation.
visma-eaccounting
Integration with Visma eAccounting API for bookkeeping and invoicing. Use when the user wants to interact with Visma eAccounting to manage invoices, customers, suppliers, upload receipts/documents, handle accounting operations, or automate bookkeeping tasks. Triggers include mentions of "Visma", "eAccounting"…
provider-cost-comparison
Prices your real LangWatch usage mix against other model providers. Exports your actual token mix per model, including the cache read and write split, fetches current price cards, and reprices the same month of usage under each candidate, with the cache sensitivity stated. Use when someone asks whether a cheaper…
billing-management
Manage XActions subscriptions and billing — view plans, start a Stripe checkout, open the billing portal, or cancel a subscription. Use when users want to upgrade, downgrade, or manage their XActions subscription.
assess
A Japanese tax-filing assessment guide that asks about your income, family, and business situation to identify which tax returns you may need.