Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jokull/icelandic-datanpx agentmods add skills/jokull/icelandic-data/financialsWrote 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/jokull/icelandic-data/financials)<a href="https://agentmods.dev/skills/jokull/icelandic-data/financials"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/financials.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.03828 |
| Opus 5 | $0.00014 | $0.01914 |
| Sonnet 5 | $0.00006 | $0.00766 |
| Haiku 4.5 | $0.00003 | $0.00383 |
Grade A, and why
financials 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 7d 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 — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financials (Annual Report Extraction)
Extract structured financial data from Icelandic annual reports (ársreikningar) using AI-powered PDF parsing.
Overview
This skill combines:
- skatturinn skill - Downloads annual report PDFs
- Docling - IBM's PDF extraction with 97.9% table accuracy
- Claude interpretation - Standardizes extracted data into structured format
Pipeline
Company kennitala
↓
skatturinn.py download (PDF)
↓
Docling (markdown + tables)
↓
Claude (structured JSON)
↓
Standardized financial data
Output Schema
interface CompanyFinancials {
// Identification
company_name: string;
kennitala: string;
fiscal_year: number;
report_type: "full" | "hnappurinn" | "consolidated";
// Income Statement (Rekstraryfirlit)
income: {
revenue: number; // Rekstrartekjur
operating_expenses: number; // Rekstrargjöld
ebitda: number; // Afkoma fyrir afskriftir
depreciation: number; // Afskriftir
ebit: number; // Afkoma fyrir fjármagnsliði
financial_income: number; // Fjármunatekjur
financial_expenses: number; // Fjármagnsgjöld
profit_before_tax: number; // Afkoma fyrir skatt
income_tax: number; // Tekjuskattur
net_profit: number; // Hagnaður/Tap ársins
};
// Balance Sheet (Efnahagsyfirlit)
balance: {
// Assets (Eignir)
fixed_assets: number; // Fastafjármunir
current_assets: number; // Veltufjármunir
total_assets: number; // Eignir samtals
// Equity & Liabilities
share_capital: number; // Hlutafé
retained_earnings: number; // Óráðstafað eigið fé
total_equity: number; // Eigið fé samtals
long_term_debt: number; // Langtímaskuldir
short_term_debt: number; // Skammtímaskuldir
total_liabilities: number; // Skuldir samtals
};
// Cash Flow (if available)
cashflow?: {
operating: number; // Handbært fé frá rekstri
investing: number; // Fjárfestingarhreyfingar
financing: number; // Fjármögnunarhreyfingar
net_change: number; // Breyting á handbæru fé
};
// Ownership (from skatturinn page or PDF)
ownership: Array<{
name: string;
kennitala?: string; // If company owner
birth_year_month?: string; // If individual (privacy)
percentage: number;
type: "direct" | "indirect";
}>;
// Corporate Structure
parent_company?: {
name: string;
kennitala: string;
ownership_pct: number;
};
subsidiaries: Array<{
name: string;
kennitala: string;
ownership_pct: number; // How much THIS company owns
book_value?: number; // Bókfært virði
equity_method: boolean; // Hlutdeildaraðferð (20-50% ownership)
}>;
associates: Array<{ // Hlutdeildarfélög (20-50% ownership)
name: string;
kennitala: string;
ownership_pct: number;
book_value?: number;
}>;
// Key Metrics (calculated)
metrics: {
equity_ratio: number; // Eiginfjárhlutfall
current_ratio?: number; // Veltufjárhlutfall
debt_to_equity?: number; // Skuldir/Eigið fé
profit_margin?: number; // Hagnaðarhlutfall
};
// Notable Events
events: Array<{
type: "acquisition" | "investment" | "dividend" | "restructuring" | "other";
description: string;
amount?: number;
}>;
// Data Quality
extraction: {
source_pdf: string;
extracted_at: string;
confidence: "high" | "medium" | "low";
notes: string[];
};
}
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.
- 7d ago First seen · 498 lines · 28 tokens per session scan A ba4ec88f35ad
financials is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 3,828 once invoked, about $0.0001 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
invoice
A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.
cwicr-report-generator
Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.
financial-document-parser
Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.