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 gewerbe-registrationgit 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/gewerbe-registration)<a href="https://agentmods.dev/skills/norman-finance/norman-mcp-server/gewerbe-registration"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/gewerbe-registration/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/gewerbe-registration"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/gewerbe-registration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 31 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00985 |
| Opus 5 | $0.00036 | $0.00492 |
| Sonnet 5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
gewerbe-registration 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 13d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through preparing their Gewerbeanmeldung (German trade-office registration, official form GewA 1, § 14 GewO): collect the data across three sections and generate a pre-filled PDF they submit themselves to their local Gewerbeamt.
Ground rules
- Who needs one: Gewerbetreibende (a trade) and GmbH/UG founders. Freiberufler (freelance professions — doctors, lawyers, artists, many IT/consulting freelancers) do not file a Gewerbeanmeldung. If the user is clearly a freelance profession, say so and don't push the flow.
- Never present anything as legal advice. The output is an auto-filled template for self-submission; it is not e-filed and not legally reviewed. Say this when the document comes up.
- The backend is the source of truth: every response carries
sections(basic / business / owner, eachcomplete+missingcamelCase field names) andstatus. Navigate bysections.missing; never track progress yourself. - Collect conversationally — a few related fields at a time, not a wall of questions.
Before you start
- Call
get_gewerbe_registration. If one exists, resume from the first incomplete section. A non-emptydocumentslist means it's already generated. If not found, offer to start one. - If the user is founding a GmbH/UG and has an incorporation, pass its publicId to
create_gewerbe_registrationso company, address, activity and managing directors are pre-filled. For self-employed users the tax-registration (Fragebogen) answers are carried over automatically. Mention that personal data (name, DOB, address) is collected for the form. - Use
get_gewerbe_registration_choicesfor the valid enum values.
Section 1 — Basics (update_gewerbe_basic)
Start of activity (activityStartDate, no more than ~14 days in the future) and whether it's a
head office or a branch (establishmentType).
Section 2 — Business (update_gewerbe_business)
Legal form, registered/business name, and — for legal entities (GmbH/UG/AG/…) — the commercial
register number. Type of business (any of industry/trade/craft/other), the Betriebsstätte
address + email, and a precise activity description (Feld 15). Offer suggest_gewerbe_activity
to sharpen the wording — show the suggestion and only apply it if the user accepts. Then the
conditionals: whether a licence/permit is required (+ authority and date), public-sector
participation, and employees (+ full-/part-time counts).
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.
- 13d ago First seen · 74 lines · 72 tokens per session scan A 03b8964efd0e
gewerbe-registration 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 985 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
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
pptx
Create and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
Read, create, inspect, merge, split, rotate, encrypt, fill, and validate PDF files. Use when the user asks to work with a PDF or convert supported Markdown into a polished PDF in AstrBot.
gather
A document-collection guide for Japanese tax filing that lists the documents needed for the filing type and explains where and how to obtain them.