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 Nolpak14/getregdata --skill icij-offshore-leaksgit clone --depth 1 https://github.com/Nolpak14/getregdataWrote 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/nolpak14/getregdata/icij-offshore-leaks)<a href="https://agentmods.dev/skills/nolpak14/getregdata/icij-offshore-leaks"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/icij-offshore-leaks/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/nolpak14/getregdata/icij-offshore-leaks"><img src="https://agentmods.dev/badge/skills/nolpak14/getregdata/icij-offshore-leaks.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 | $0.00177 | $0.02471 |
| Opus 5 | $0.00088 | $0.01236 |
| Sonnet 5 | $0.00035 | $0.00494 |
| Haiku 4.5 | $0.00018 | $0.00247 |
Grade A, and why
icij-offshore-leaks 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 10d 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.
curl -s "https://offshoreleaks.icij.org/api/v1/reconcile" \ How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
icij-offshore-leaks
Search a name against the ICIJ Offshore Leaks Database - the offshore leg of an enhanced due-diligence (EDD) check. Take the entity and the beneficial owners / directors you extracted from a registry, and ask a single question: does any of them appear in the offshore leaks? This runs on ICIJ's public database aggregating the Panama Papers, Paradise Papers, Pandora Papers, Bahamas Leaks and the original Offshore Leaks - free and keyless. But read the disclaimer below before you read a single result: this is leak data, and appearing in it is a red flag to investigate, never a finding of wrongdoing.
ICIJ disclaimer (carry this on every output): "ICIJ does not intend to suggest or imply that any individuals, companies or other entities included in the Offshore Leaks Database have broken the law or otherwise acted improperly. There are legitimate uses for offshore companies and trusts."
Persona
You are an enhanced due-diligence analyst running the offshore-structure lane of a screen. You search customers, counterparties, and their beneficial owners for exposure to leaked offshore data, you understand that a name match is a candidate to verify - not a hit, and never proof of wrongdoing (ICIJ itself disclaims that reading; there are legitimate reasons to hold an offshore company or trust) - and you keep offshore exposure separate from sanctions, litigation and debarment: distinct data problems that together make one screen.
What this gives you (for free)
- Entities - the offshore companies, trusts and foundations named in the leaks: name, jurisdiction of incorporation, linked country, incorporation/struck-off dates, and the source leak.
- Officers - the people and companies connected to those entities (shareholders, directors, beneficiaries).
- Intermediaries - the go-betweens (law firms, agents, banks) that set up or managed the structures.
- Addresses - the registered addresses tying the records together - the key corroborator for confirming a common-name match.
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.
- 10d ago First seen · 141 lines · 177 tokens per session scan A fd81769b406f
icij-offshore-leaks is a skill published in the GitHub repository Nolpak14/getregdata (6 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 2,471 once invoked, about $0.0009 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.
Other skills, from other repositories
apify-ads-intelligence
Research, spy on, and analyze ads across Meta (Facebook & Instagram), Google (Ads Transparency Center + paid search results), TikTok (Ads Library + Creative Center), LinkedIn Ad Library, and X (Twitter — promoted tweets, best-effort) using Apify Actors. Use when user asks about competitor ads, ad library research…
apify-ecommerce
Scrape e-commerce data for pricing, reviews, bestsellers, and seller discovery across 30+ platforms including Amazon, Walmart, eBay, Shopify, WooCommerce, and more. Use when user asks about product prices, competitor analysis, store scraping, tech stack detection, food delivery, real estate, or marketplace…
apify-google-maps-leads
Build a local-business lead database from Google Maps in one Apify pipeline: search by target audience + geography, enrich each place with company contacts from its website, leads enrichment (names, emails, phones, LinkedIn), Instagram + Facebook profiles, and optionally reviews for lead scoring. For places with no…
apify-lead-scoring-enrichment
Score and enrich a CSV of B2B leads using Apify Actors. Takes a CSV with company URLs, free-text scoring rules, and an enrichment preference; runs BuiltWith (tech stack), Website Content Crawler (content classification), and Contact Info Scraper (company metadata) for scoring; enriches with either department-specific…
apify-local-business-leads-osm
Build a local-business lead list without scraping Google Maps. Routes "find dentists / plumbers / salons / restaurants in with emails", "business email finder for in ", "web-design prospects with no website or a weak one", "enrich my list of business websites with verified emails", "leads within 5 km of an address"…
apify-osint-threat-intel
Use this skill when the user asks to "find CVEs for", "check if my domain is breached", "threat intel on", "OSINT on", "security news about", "attack surface of", "is this IP malicious", "what vulnerabilities affect", "security advisory for", "monitor threats for", "threat actor research", "recent exploits for", "data…