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/calendar-syncWrote 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/calendar-sync)<a href="https://agentmods.dev/skills/dithiothreitol/jdg-ksiegowy/calendar-sync"><img src="https://agentmods.dev/badge/skills/dithiothreitol/jdg-ksiegowy/calendar-sync/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/calendar-sync"><img src="https://agentmods.dev/badge/skills/dithiothreitol/jdg-ksiegowy/calendar-sync.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 | $0.00148 | $0.00768 |
| Opus 5 | $0.00074 | $0.00384 |
| Sonnet 5 | $0.00030 | $0.00154 |
| Haiku 4.5 | $0.00015 | $0.00077 |
Grade A, and why
calendar-sync 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.
What it actually says
Synchronizacja terminów podatkowych z Google Calendar
Czyta przypomnienia z dashboardu (status/dashboard.py — terminy podatkowe + niezapłacone/zaległe
faktury, z kwotami) i uzgadnia je z kalendarzem „JDG Podatki" przez Google Calendar API.
Wydarzenia całodniowe na termin płatności, z popupami N dni przed i w dniu.
Wymagana konfiguracja (jednorazowo)
- Google Cloud Console → utwórz OAuth client ID typu „Desktop app", pobierz
credentials.json. - W
.env:GCAL_ENABLED=true,GCAL_CREDENTIALS_PATH=/sciezka/credentials.json. python -m jdg_ksiegowy.calendar.auth_setup— jednorazowa zgoda w przeglądarce (zapisuje refresh token).
Jeśli skrypt zwróci błąd „nie skonfigurowany" / „Brak tokenu" — przerwij i poprowadź usera przez powyższe kroki.
Wywołanie
# Podglad (NIC nie zapisuje) — pokaz co by sie zmienilo:
python3 skills/calendar-sync/scripts/sync.py --dry-run
# Synchronizacja:
python3 skills/calendar-sync/scripts/sync.py
Zwraca JSON: created / updated / deleted / unchanged (listy kluczy wydarzeń) + dry_run.
Zachowanie
- Idempotentne: ponowne uruchomienie bez zmian → wszystko w
unchanged. - Kwoty się aktualizują: zmiana szacowanej kwoty (np. po dodaniu faktury/kosztu) →
updated. - Zapłacone faktury znikają: po oznaczeniu faktury jako zapłaconej jej przypomnienie wypada z dashboardu → wydarzenie zostaje usunięte z kalendarza.
- Dotyka wyłącznie wydarzeń utworzonych przez aplikację (oznaczonych
jdg_managed) — nigdy nie rusza prywatnych wpisów usera.
Automatyzacja
Cron OpenClaw odpala to codziennie (patrz CRON.md): 0 7 * * *. Dzięki temu kwoty są świeże,
a zapłacone faktury automatycznie znikają.
Uwagi
- Kwota VAT+JPK jest szacunkowa (należny − naliczony za poprzedni miesiąc); autorytatywna kwota
pochodzi ze skilla
jpk. - Nigdy nie loguj tokenu OAuth do outputu.
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 · 51 lines · 148 tokens per session scan A f9a929f4aa02
calendar-sync is a skill published in the GitHub repository dithiothreitol/jdg-ksiegowy (5 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 768 once invoked, about $0.0007 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
subscription-management
Track, analyze, and optimize all SaaS subscriptions — renewals, usage analysis, cost optimization, vendor consolidation, and cancellation workflows.
USMetrics
Analyze and update 68 US economic and social indicators from five government APIs (FRED, EIA, Treasury, BLS, Census) across 10 categories: GDP, Inflation, Employment, Housing, Consumer Finance, Markets, Trade, Government/Fiscal, Demographics, Health. Two workflows: UpdateData, GetCurrentState (10y/5y/2y/1y trend…
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
converge
Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrongif falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic…
airdrop-hunter
Airdrop tracking and qualification automation.
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.