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/plugins/matematicsolutions/awesome-matematic-skills-pl/orzecznictwo-zrodla)<a href="https://agentmods.dev/plugins/matematicsolutions/awesome-matematic-skills-pl/orzecznictwo-zrodla"><img src="https://agentmods.dev/badge/plugins/matematicsolutions/awesome-matematic-skills-pl/orzecznictwo-zrodla/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/plugins/matematicsolutions/awesome-matematic-skills-pl/orzecznictwo-zrodla"><img src="https://agentmods.dev/badge/plugins/matematicsolutions/awesome-matematic-skills-pl/orzecznictwo-zrodla.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
orzecznictwo-zrodla 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 12d 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
{
"name": "orzecznictwo-zrodla",
"description": "Wyszukiwanie i pobieranie źródeł prawa PL/UE: SAOS, EUR-Lex, katalog źródeł krajowych. Niesie konektory MCP saos/krs/eu-sparql (read-only, publiczne API). Wymaga node/npx.",
"version": "1.3.0",
"author": { "name": "Wiesław Mazur / MateMatic Solutions" },
"homepage": "https://github.com/matematicsolutions/awesome-matematic-skills-pl",
"license": "Apache-2.0",
"keywords": ["legal-ai", "polish-law", "case-law", "eur-lex", "saos", "mcp", "rodo-safe"]
}
What it installs
The manifest is a name and a version. 8 skills, 3 commands travel with it, and installing the plugin installs all of them — 1,809 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill eu-sparql-search A 147 tokens
- Skill hierarchia-zrodel-pl A 212 tokens
- Skill legal-data-hunter-pl A 211 tokens
- Skill saos-orzecznictwo A 186 tokens
- Skill uodo-grounding-pl A 280 tokens
- Skill webwright-legal-pl A 88 tokens
- Skill struktura-wyroku-pl A 274 tokens
- Skill szukaj-orzeczen-v2 A 304 tokens
- Command szukaj A 35 tokens
- Command eurlex A 31 tokens
- Command orzeczenie A 41 tokens
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.
- 12d ago First seen · 10 lines scan A 822a4fbf7242
orzecznictwo-zrodla is a plugin published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
patent-aid
AI patent writing skills: from idea to submission-ready patent disclosure (docx) with anti-hallucination checks and claim-format validation. Works for any technical domain.
compliance-review
Build or review code for compliance with the EU AI Act, GDPR, the NIS2 Directive (EU 2022/2555), and secure-development (SSDLC) best practice. Three modes: repo gap analysis, compliance-by-design while coding, and data protection — the skill asks whether to pseudonymise (deterministic tokens, joins preserved) or…
legal-audit-de
Multi-platform plugin (Claude Code, Codex CLI, GitHub Copilot CLI) for German/EU legal audits (DSGVO, TDDDG, UWG, AI Act, DDG, BGB, BFSG, UrhG, KUG, MarkenG, NIS2). Scans codebases, live URLs, and individual legal documents; produces severity-classified findings + clean corrected versions. NOT legal advice.
lians
Financial-grade agent memory for Claude Code — bitemporal recall, SEC 17a-4 audit chain, GDPR/HIPAA crypto-shred, and information barriers. Built for finance, healthcare, and legal teams.
section-508
Expert Section 508 compliance advisor for US federal ICT accessibility — VPAT/ACR completion, WCAG 2.0 AA audits, remediation planning, PDF accessibility, procurement language, keyboard and screen reader testing, undue burden assessments, and agency compliance workflows.
fedramp-ssp
Convert FedRAMP Rev 5 Moderate SSP DOCX templates to validated OSCAL 1.2.0 JSON. Wraps ethanolivertroy/frdocx-to-froscal-ssp — ready for oscal-cli, Compliance Trestle, eMASS, and FedRAMP 20X workflows.