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 company-incorporationgit 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/company-incorporation)<a href="https://agentmods.dev/skills/norman-finance/norman-mcp-server/company-incorporation"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/company-incorporation/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/company-incorporation"><img src="https://agentmods.dev/badge/skills/norman-finance/norman-mcp-server/company-incorporation.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 26 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 | $0.00073 | $0.01643 |
| Opus 5.5 | $0.00029 | $0.00657 |
| Sonnet 5.5 | $0.00015 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
company-incorporation 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through founding a German GmbH or UG (haftungsbeschränkt): collect the data, generate pre-filled founding document drafts, and hand off to a notary.
Ground rules
- Never present anything as legal advice. The generated documents are auto-filled templates (drafts) to prepare the notary appointment; the notary produces the binding versions. Say this whenever documents come up.
- The backend is the source of truth: every tool response carries
sections(per-sectioncomplete+missing),musterprotokoll(eligible+reasons) andstatus. Navigate bysections.missing; never track progress yourself. - Collect conversationally — one topic at a time, not a wall of questions.
- Amounts are full euros (§ 5 Abs. 2 GmbHG: nominal amounts in whole euros).
Before you start
- Call
get_incorporation. If one exists, resume from the first incomplete section and summarize what's already collected. If not found, briefly explain the journey (data → documents → notary) and callcreate_incorporation. SavepublicId. - Mention that personal data of the founders (name, DOB, address) will be collected to prepare the documents and the notary hand-off.
Section 1 — Company (update_incorporation_company)
- Legal form: UG (haftungsbeschränkt) or GmbH. If the user is unsure: UG founds from 1 € capital but must retain earnings to build reserves; GmbH needs 25,000 € (half paid in before registration) and carries more weight with partners/banks. Side effect worth mentioning: choosing the legal form switches the user's Norman account to that corporate type with the SKR04 chart of accounts (out of the freelancer default), so bookkeeping and taxes are set up correctly from the start.
- Company name. The legal suffix is appended automatically. After saving, offer
check_incorporation_name— it searches the Handelsregister for similar registered names.status="unavailable"means the portal couldn't be reached (say so; don't imply the name is free); matches mean a similar name may be rejected. Final say is the registry court + IHK. - Business purpose (Unternehmensgegenstand): a short concrete sentence. If the user's
wording is rough, offer
suggest_incorporation_purpose— it returns a registry-ready rewrite; show it and let them accept or keep their own, then save via update_incorporation_company. Never auto-apply it. - Registered office city (Sitz) is required; the street address can be skipped for now
(
registered_address_skipped=true) but is needed before notarization — mention Norman can help with a business address later.
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.
- 5d ago Changed · +3 tokens per session 453871f7961e
- 1mo ago First seen · 121 lines · 70 tokens per session scan A 7cb473e1f59b
company-incorporation is a skill published in the GitHub repository norman-finance/norman-mcp-server (62 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,643 once invoked, about $0.0003 per session on Opus 5.5. 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
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
assess
A Japanese tax-filing assessment guide that asks about your income, family, and business situation to identify which tax returns you may need.
incorporation
A guide for moving from working as an individual business owner to operating through a company in Japan. It covers company types, setup steps, officer pay, taxes, and social insurance.
tax-ebookkeeping-context
Background information about Japan’s Electronic Bookkeeping Act, which sets rules for storing accounting records, scanned documents, and data received through electronic transactions.
tax-housing-loan-context
Background rules for Japan’s housing-loan tax credit, including eligibility, credit limits, calculation rules, and its relationship with hometown donations.