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.
npx skills add matematicsolutions/awesome-matematic-skills-pl --skill legal-ai-audit-bundlegit 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/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle)<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle/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/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle.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 | $0.00220 | $0.04200 |
| Opus 5.5 | $0.00088 | $0.01680 |
| Sonnet 5.5 | $0.00044 | $0.00840 |
| Haiku 4.5 | $0.00022 | $0.00420 |
Grade A, and why
legal-ai-audit-bundle 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 21d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal AI Audit Bundle - artefakt zgodności dla outputu AI prawnego
Filozofia
Jeśli nie potrafisz odtworzyć, jak AI doszło do wyniku, nie powinieneś wysyłać tego wyniku.
AI Act art. 12 wymaga rejestrowania zdarzeń (prowadzenia rejestrów) dla systemów wysokiego ryzyka, art. 14 - nadzoru człowieka, art. 50 - poinformowania osoby, że treść została wygenerowana przez AI. Dla kancelarii używającej AI w pracy z klientem oznacza to: dla każdego istotnego deliverable musi istnieć ślad - jaki model, jakie źródła, jaka weryfikacja, jaki koszt, kto zatwierdził. Ten skill składa ten ślad w jedną paczkę z hashami integralności, tak by dało się ją odtworzyć i wykazać przy audycie.
To nie jest deliverable dla klienta. To deliverable dla audytora, regulatora i Twojej własnej odpowiedzialności zawodowej.
Co wchodzi do paczki
| Artefakt | Źródło | Wymagane |
|---|---|---|
| Deliverable finalny | praca prawna | TAK |
| Ślad rozumowania | transcript adversarial-legal-review-pl lub log analizy |
TAK dla high-stakes |
| Raport grounding | output citation-grounding-pl |
TAK jeśli były cytaty |
| Log kosztu | tokeny / koszt przebiegów | TAK |
| Metadane | model, wersja, data, źródła, autor, zatwierdzający | TAK |
| Pseudonimizacja | mapa let-it-be (jeśli użyta) - TRZYMANA OSOBNO, nie w paczce |
warunkowo |
Workflow
-
Zbierz artefakty - upewnij się, że istnieją pliki: deliverable, transcript/ślad, raport grounding, log kosztu. Brakujące oznacz w manifeście jako
MISSING- paczka i tak powstaje, ale z widoczną luką (audytor musi widzieć, czego nie ma). -
Opisz manifest - przygotuj descriptor JSON (patrz FORMAT) z metadanymi i ścieżkami do artefaktów.
-
Złóż paczkę - uruchom skrypt:
node scripts/assemble-bundle.mjs <descriptor.json> <katalog-docelowy>Skrypt: kopiuje artefakty do ustrukturyzowanego folderu, liczy SHA256 każdego pliku (integralność), generuje
manifest.json+ czytelnyINDEX.md. -
Zweryfikuj kompletność - skrypt zwraca listę
MISSINGi ostrzega, jeśli brak record-keepingu wymaganego dla high-stakes. Uzupełnij albo świadomie odnotuj brak.
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.
- 21d ago Changed · +32 lines 3e9946223055
- 1mo ago First seen · 211 lines · 220 tokens per session scan A 61f91854e7fa
legal-ai-audit-bundle is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (8 stars, last pushed 8d ago), licensed MIT. It adds 220 tokens to every session and 4,200 once invoked, about $0.0009 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 skills, from other repositories
mqc-timeline-master
Turn raw case materials into a faithful, court-ready case timeline (SVG + PNG + PPTX + VSDX + drawio, plus a traceability index in Word). Use this whenever the user hands over litigation materials — a judgment, complaint, defence, evidence list, contract, bank or Alipay statement, WeChat screenshots, scanned exhibits…
mqc-litigation-visual-redraw
Redraw a litigation diagram into a restrained, court-ready presentation graphic (SVG + PNG) WITHOUT changing any text or legal meaning. Use this whenever the user supplies a case timeline, a legal process flowchart, OR a party/relationship diagram and wants it cleaned up, beautified, redrawn, made professional…
universal-standards
LegalAnt operating protocol — HITL gates, citation completeness, hallucination defence, Indian law default, data security, and mandatory disclaimer. Applies to every agent on every matter.
niw-package-review
Reviews an assembled EB-2 NIW petition package before filing, as a skeptical adjudicator would. Reads the actual exhibits, recommendation letters and petition draft, tests each Dhanasar prong against the preponderance standard on documented evidence only, quotes the specific petition passages that overclaim, and…
niw-rfe-response
Works a USCIS Request for Evidence or Notice of Intent to Deny on an EB-2 NIW petition, from reading the notice through to a drafted response. Reads the printed deadline rather than computing one, crosswalks each contested issue against the record as actually filed, stops for the petitioner to correct what it found…
indian-law-defaults
Indian statute and regulatory hierarchy defaults. All agents assume Indian jurisdiction unless overridden. Auto-triggers FEMA for foreign counterparties and SEBI LODR for listed entities.