Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jamarpl21/prawo-pl-eli/plugin install prawo-pl-orzeczenia-msWrote 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/jamarpl21/prawo-pl-eli/prawo-pl-orzeczenia-ms)<a href="https://agentmods.dev/skills/jamarpl21/prawo-pl-eli/prawo-pl-orzeczenia-ms"><img src="https://agentmods.dev/badge/skills/jamarpl21/prawo-pl-eli/prawo-pl-orzeczenia-ms/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/jamarpl21/prawo-pl-eli/prawo-pl-orzeczenia-ms"><img src="https://agentmods.dev/badge/skills/jamarpl21/prawo-pl-eli/prawo-pl-orzeczenia-ms.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 | $0.00165 | $0.02304 |
| Opus 5.5 | $0.00066 | $0.00922 |
| Sonnet 5 | $0.00033 | $0.00461 |
| Haiku 4.5 | $0.00016 | $0.00230 |
Grade A, and why
prawo-pl-orzeczenia-ms 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 6d 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.
import hashlib, os, sys, urllib.request How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portal Orzeczeń Sądów Powszechnych MS
Źródło pierwotne: https://orzeczenia.ms.gov.pl. Publikuje wybór zanonimizowanych orzeczeń SA/SO/SR. Brak wyniku nie dowodzi braku wyroku. SAOS pozostaje wygodnym agregatem do ogólnego researchu; ten skill służy dostępowi do źródła i nowszych publikacji.
Uruchomienie
Helper scripts/orzeczenia_ms.py obok tego SKILL.md wymaga tylko Python 3.8+ i sieci.
Korzysta z HTTPS, walidacji certyfikatu i odstępu ≥0,6 s między żądaniami w procesie.
Nie wymaga klucza, instalacji bibliotek ani przeglądarki. Uruchamiaj helper z tego pakietu:
# 1) Claude Code: przy ładowaniu skilla podstawia ${CLAUDE_PLUGIN_ROOT} (pełna ścieżka poniżej).
MS="${CLAUDE_PLUGIN_ROOT}/skills/prawo-pl-orzeczenia-ms/scripts/orzeczenia_ms.py"
# 2) Codex / Claude Desktop / instalacja ręczna: katalog TEGO pliku SKILL.md (Claude Code podaje go
# jako „Base directory for this skill”, Codex w liście skilli) — podstaw go zamiast <katalog skilla>.
[ -f "$MS" ] || MS="<katalog skilla>/scripts/orzeczenia_ms.py"
# 3) Piaskownica (Cowork, czat z code execution): katalog pluginu bywa NIEWIDOCZNY dla powłoki — wtedy
# pobierz DOKŁADNIE tę wersję helpera (tag = wersja z nagłówka tego pliku). Suma SHA-256 jest
# sprawdzana w kodzie przed zapisem i przed każdym uruchomieniem; niezgodna = helper nie startuje.
[ -f "$MS" ] || MS=$(python3 - <<'EOF'
import hashlib, os, sys, urllib.request
WERSJA, SHA256 = "2.1.0", "d1d64a6f945b6d434ad8cb8311fdc6885ec3ad54b94973e92cd6abde33f4efd5"
URL = f"https://raw.githubusercontent.com/jamarpl21/prawo-pl-eli/v{WERSJA}/plugins/prawo-pl-orzeczenia-ms/skills/prawo-pl-orzeczenia-ms/scripts/orzeczenia_ms.py"
p = os.path.join(os.environ.get("TMPDIR", "/tmp"), f"prawo-pl-orzeczenia-ms-{WERSJA}", "orzeczenia_ms.py")
try:
dane = open(p, "rb").read() if os.path.exists(p) else urllib.request.urlopen(URL, timeout=30).read()
except Exception as e:
sys.exit(f"BŁĄD: nie udało się pobrać helpera ({e}). Bez helpera NIE cytuj prawa z pamięci ani z portali — poinformuj użytkownika.")
if hashlib.sha256(dane).hexdigest() != SHA256:
os.path.exists(p) and os.remove(p)
sys.exit("BŁĄD: suma SHA-256 helpera nie zgadza się z SKILL.md — helper NIE zostanie uruchomiony. Nie cytuj prawa z pamięci ani z portali — poinformuj użytkownika.")
os.makedirs(os.path.dirname(p), exist_ok=True); open(p, "wb").write(dane); print(p)
EOF
) && [ -f "$MS" ] || exit 1
python3 "$MS" <komenda> [...]
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 114 lines · 165 tokens per session scan A 7cb894b53300
prawo-pl-orzeczenia-ms is a skill published in the GitHub repository jamarpl21/prawo-pl-eli (17 stars, last pushed 6d ago), licensed MIT. It adds 165 tokens to every session and 2,304 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-20.
Other skills, from other repositories
contract-drafter
Drafts a complete contract from a term sheet, negotiated heads or plain instructions — parties, recitals, definitions, operative clauses, schedules and boilerplate — in a specified posture and matched to a supplied or requested precedent. Covers any commercial agreement type directly, and via specialist references…
clause-comparator
Compares the same clause or provision across draft rounds, precedents, public agreements or a portfolio and reports what differs in wording and effect. Use for version-change requests and external clause benchmarking, including "what changed between drafts", "compare their indemnity with ours", "compare liability caps…
indemnity-liability-analyst
Analyses the warranty, indemnity, exclusion, cap and insurance provisions in a contract as one interacting system for one identified party. Use for focused prompts such as "what is our exposure under this indemnity", "does the cap still protect the Supplier after the carve-outs", "which liabilities are capped or…
investment-and-shareholder-agreement-reviewer
Reviews venture and private-investment documents — term sheets, letters of intent, share subscription agreements, shareholders' agreements, investment agreements, joint-venture agreements, constitutional rights packages, and side letters — from one identified party's position (founder, investor, majority, minority…
legal-opinion-drafter
Drafts a structured written legal opinion — the question presented, the facts relied on, the analysis, the conclusion, and the assumptions and limitations it depends on. Includes a tax-opinion mode adding the risk-characterisation, exposure-if-challenged, and disclosure-obligation dimensions a tax position…
obligations-extractor
Pulls every obligation, deadline, condition and notice requirement out of a contract into a structured ledger, without evaluating whether any of it is fair, onerous or negotiable. Use this whenever a user wants a list, table or calendar of what a contract actually requires — including phrasings like "list every…