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.
git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-plWrote 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/commands/matematicsolutions/awesome-matematic-skills-pl/szukaj)<a href="https://agentmods.dev/commands/matematicsolutions/awesome-matematic-skills-pl/szukaj"><img src="https://agentmods.dev/badge/commands/matematicsolutions/awesome-matematic-skills-pl/szukaj/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/commands/matematicsolutions/awesome-matematic-skills-pl/szukaj"><img src="https://agentmods.dev/badge/commands/matematicsolutions/awesome-matematic-skills-pl/szukaj.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 | $0.00035 | $0.00543 |
| Opus 5.5 | $0.00014 | $0.00217 |
| Sonnet 5.5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
szukaj 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.
What it actually says
You are the Webwright agent in CLI tool mode. Your task: produce a
parameterized Python script szukaj_orzeczen.py that searches Polish court
portals by keyword phrase and returns a structured JSON results list.
Task arguments: $ARGUMENTS
Read ../SKILL.md for the full output contract and RODO notes before starting.
Routing
Domyślnie szukaj na orzeczenia.ms.gov.pl (sądy powszechne).
Jeśli w argumencie pojawi się "SN", "Sąd Najwyższy" lub "CSK" → szukaj też na www.sn.pl.
Script contract
python szukaj_orzeczen.py \
--fraza "dobro dziecka" \
--sad "Sąd Apelacyjny" \
--limit 10 \
--output-dir outputs/szukaj/
Writes outputs/szukaj/<slug>/wyniki.json:
{
"fraza": "...",
"sad": "...",
"limit": 10,
"pobrano_at": "ISO8601",
"zrodlo": "orzeczenia.ms.gov.pl",
"wyniki": [
{"sygnatura": "...", "sad": "...", "data": "...", "url": "...", "fragment": "..."}
]
}
Log kończy się FINAL_RESPONSE: <liczba wyników> orzeczeń.
Playwright notes
- Firefox, headless, viewport 1280×1800
- orzeczenia.ms.gov.pl: pole "Treść orzeczenia" lub "Słowa kluczowe" → wpisz frazę → "Szukaj" Zbierz z listy wyników: sygnatura, sąd, data, URL wyniku, fragment tekstu
- sn.pl: zakładka "Orzecznictwo" → wyszukiwarka pełnotekstowa → fraza
- Retry 3s jeśli 503
- Limit: pobierz maksymalnie
--limitwyników (domyślnie 10), nie wchódź w treść każdego
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 · 53 lines · 35 tokens per session scan A 7a80f2adf3ef
szukaj is a command published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (8 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 543 once invoked, about $0.0001 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 commands, from other repositories
advise
Map the regulatory perimeter for a transaction or business activity.
arbitrate
Prepare arbitration strategy, bundle, and timeline under A&C Act 1996.
dd
Run a 12-step legal due diligence across 4 parallel streams.
litigate
Prepare pleadings, strategy, and evidence analysis for litigation.
realestate
Conduct real estate due diligence, title analysis, and transaction review.
chronology
Build a timeline of events from uploaded documents.