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/dithiothreitol/jdg-ksiegowynpx agentmods add skills/dithiothreitol/jdg-ksiegowy/jpk-submitWrote 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/dithiothreitol/jdg-ksiegowy/jpk-submit)<a href="https://agentmods.dev/skills/dithiothreitol/jdg-ksiegowy/jpk-submit"><img src="https://agentmods.dev/badge/skills/dithiothreitol/jdg-ksiegowy/jpk-submit/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/dithiothreitol/jdg-ksiegowy/jpk-submit"><img src="https://agentmods.dev/badge/skills/dithiothreitol/jdg-ksiegowy/jpk-submit.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 | $0.00157 | $0.01187 |
| Opus 5 | $0.00078 | $0.00593 |
| Sonnet 5 | $0.00031 | $0.00237 |
| Haiku 4.5 | $0.00016 | $0.00119 |
Grade A, and why
jpk-submit 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 11d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wysyłka JPK do bramki MF
Pełny flow: szyfrowanie XML (AES-256-CBC + RSA klucz publiczny MF) → init upload → PUT na Azure Blob → finish → polling status → pobranie UPO.
Wymagane dane
- xml-path — ścieżka do pliku JPK (zwykle z
data/jpk/JPK_V7M_*.xmllubdata/jpk/JPK_EWP_*.xml)
W .env muszą być:
MF_PESEL— PESEL podatnikaMF_PRIOR_INCOME— kwota przychodu z PIT za rok N-2 (dla wysyłki w 2026 → PIT za 2024). Pozycje zgodnie z formularzem PIT-37/28/36/36L. Brak zeznania →0.MF_CERT_PATH— ścieżka do klucza publicznego MF (PEM/DER) — pobierz z podatki.gov.pl, sekcja klucze publiczneMF_ENV=test(domyślnie) lubprodSELLER_FIRST_NAME,SELLER_LAST_NAME,SELLER_BIRTH_DATE,SELLER_NIP
Wywołanie — DRY-RUN (zalecane przed pierwszą wysyłką)
python3 skills/jpk-submit/scripts/submit.py --xml-path data/jpk/JPK_V7M_2026_04.xml --dry-run
Pokazuje co byłoby wysłane (rozmiar, env, fingerprint danych autoryzujących) bez dotykania bramki.
Wywołanie — wysyłka
python3 skills/jpk-submit/scripts/submit.py --xml-path data/jpk/JPK_V7M_2026_04.xml
Zwraca JSON:
{
"success": true,
"reference_number": "20260417-...",
"status_code": 200,
"upo_path": "data/upo/UPO_20260417-...bin",
"mf_env": "test"
}
Polling statusu trwa do 10 minut (interwał 15s). Status 200 = sukces + UPO; 401-420 = błędy MF (zła XSD, certyfikat, autoryzacja).
⚠️ KRYTYCZNE — przed wysyłką na PROD
- Najpierw przetestuj na bramce TEST (
MF_ENV=test). Bramka prod =e-dokumenty.mf.gov.pl, test =test-e-dokumenty.mf.gov.pl. - Zweryfikuj kwotę przychodu z PIT za rok N-2 — błąd → odrzucenie autoryzacji. Konkretne pozycje: PIT-37 poz. 50/83, PIT-28 poz. 20/22/24/62/73, PIT-36 poz. 67-75/131, PIT-36L poz. 23/25/27/28/33. Brak zeznania = 0. Nie wolno sumować z różnych zeznań.
- Sprawdź certyfikat MF — aktualizowany okresowo (ostatnio 18.07.2025). Nieaktualny → init zwróci błąd
404. - Zachowaj UPO —
data/upo/UPO_*.binto dowód złożenia. Bez UPO uznaje się że JPK nie został złożony. - Termin — JPK_V7M do 25-go następnego miesiąca; JPK_EWP do 30.04 następnego roku.
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.
- 11d ago First seen · 64 lines · 157 tokens per session scan A fe34074529dd
jpk-submit is a skill published in the GitHub repository dithiothreitol/jdg-ksiegowy (5 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 1,187 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
tax-calculator
Calculate tax implications of trades and generate tax reports.
jangbu-import
A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.
jangbu-connect
A setup guide for connecting Korean tax, bank, card, and social-insurance data through CODEF, an external API service. It explains how users obtain their own CODEF credentials and store them locally.
jangbu-tax
A financial-reporting tool that summarizes categorized transactions into a profit-and-loss statement and a simplified balance sheet. A profit-and-loss statement covers income and expenses over a period; a balance sheet shows assets, liabilities, and equity at a date.
accountant-expert
Expert-level accounting, tax, financial reporting, and accounting systems. Use when the user mentions accounting, tax, financial reporting, GAAP, or IFRS, or when the task involves Accounting Principles, Financial Statements, Tax & Compliance, or Accounting Systems.
jaz-recipes
Use this skill when modeling complex multi-step accounting transactions — anything that spans multiple periods, involves changing amounts, or requires linked entries. Covers 16 IFRS-compliant recipes (prepaid amortization, deferred revenue, loans, IFRS 16 leases, hire purchase, fixed deposits, asset disposal, FX…