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 Hei33enberg/WhiteIntel-OS --skill corporate-ownership-investigationgit clone --depth 1 https://github.com/Hei33enberg/WhiteIntel-OSWrote 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/hei33enberg/whiteintel-os/corporate-ownership-investigation)<a href="https://agentmods.dev/skills/hei33enberg/whiteintel-os/corporate-ownership-investigation"><img src="https://agentmods.dev/badge/skills/hei33enberg/whiteintel-os/corporate-ownership-investigation/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/hei33enberg/whiteintel-os/corporate-ownership-investigation"><img src="https://agentmods.dev/badge/skills/hei33enberg/whiteintel-os/corporate-ownership-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00117 | $0.02200 |
| Opus 5.5 | $0.00047 | $0.00880 |
| Sonnet 5.5 | $0.00023 | $0.00440 |
| Haiku 4.5 | $0.00012 | $0.00220 |
Grade A, and why
corporate-ownership-investigation 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 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.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Corporate ownership investigation
Answer "who really owns this company?" from public registries — and, just as importantly, know when the honest answer is "we cannot see that from here".
Why this skill exists
Ownership questions are where confident-sounding answers do the most damage. A due-diligence sentence like "X has no offshore exposure" is a claim about the whole world; what the data usually supports is "no exposure over the two hops we could walk". This skill is mostly about that gap: the calls are easy, the honest reading is not.
Setup
Either transport works; no account and no key are needed for the free tier.
- MCP (preferred):
npx -y @whiteintel/mcp-server— 24 tools. Hosted alternative for clients that cannot spawn a subprocess: POST JSON-RPC 2.0 tohttps://whiteintel.dev/api/mcp. - Plain HTTP:
https://whiteintel.dev/api/public/*— same data, no install. Every page also has a markdown twin for reading: append.mdto an entity or hub URL.
Set WHITEINTEL_API_KEY (a wi_ key) only if you have one — it lifts depth caps.
The core loop
1. Resolve the name to an id — never investigate a string
search_entities { q: "Acme Holdings", juris: "gb" } # lexical, covers the FULL corpus
resolve { queries: ["gb-coh:00445790", "Acme Holdings"] } # batch; identifiers beat names
A name match is a candidate, not a resolution. Measured: "Tesco" resolves to a French
company literally named TESCO, while gb-coh:00445790 resolves exactly to Tesco PLC. If you hold
any registry identifier (LEI, company number, SIREN, CNPJ, UEN, CIK), pass that instead —
lookup_by_identifier takes eleven schemes.
Before reporting "not found", try both search_entities (lexical, full corpus) and
semantic_search (meaning-based but only ~2% embedded and skewed to risk-listed people).
An empty semantic result usually means "not embedded", not "does not exist".
2. Check what coverage you actually have for that country
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.
- 1mo ago First seen · 172 lines · 117 tokens per session scan A 2b21d600e8ff
corporate-ownership-investigation is a skill published in the GitHub repository Hei33enberg/WhiteIntel-OS (1 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,200 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
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…
Canada (Federal) — Corporations Canada Lookup
Live, real-time queries to Corporations Canada (CBCA) (Canada (Federal)). Drops the OpenRegistry MCP toolset onto a single-country workflow when the user names Corporations Canada, the country, or its registry directly. ID format: 7-digit federal CBCA number (e.g. 1234567). Returns the registry's response unmodified …
Czechia — ARES Lookup
Live, real-time queries to ARES — Administrativní registr ekonomických subjektů (Czechia). Drops the OpenRegistry MCP toolset onto a single-country workflow when the user names ARES, the country, or its registry directly. ID format: 8-digit IČO (e.g. 45274649 for ČEZ a.s.). Returns the registry's response unmodified …
Germany — Handelsregister Lookup
Live, real-time queries to Handelsregister (Germany). Drops the OpenRegistry MCP toolset onto a single-country workflow when the user names Handelsregister, the country, or its registry directly. ID format: Court-prefixed Handelsregister number (e.g. HRB 123456 B Berlin, HRB 12345 München). Returns the registry's…
Italy — Registro Imprese (BRIS) Lookup
Live, real-time queries to Registro delle imprese (InfoCamere via EU BRIS) (Italy). Drops the OpenRegistry MCP toolset onto a single-country workflow when the user names Registro Imprese (BRIS), the country, or its registry directly. ID format: Italian Codice Fiscale or REA number (REA: MI-1234567 Milan or RM-1234567…
Monaco — RCI Monaco Lookup
Live, real-time queries to RCI — Répertoire du Commerce et de l'Industrie (Monaco). Drops the OpenRegistry MCP toolset onto a single-country workflow when the user names RCI Monaco, the country, or its registry directly. ID format: RCI number (e.g. 99 S 03847 formatted, sequential). Returns the registry's response…