legal-ai-audit-bundle

legal-ai-audit-bundle is a skill for Claude Code from matematicsolutions/awesome-matematic-skills-pl. It costs 220 tokens per session (3,540 once invoked), scanned A, original, MIT.

A package builder for preserving the audit trail of AI-generated legal work under Article 12 of the EU AI Act. It combines the final document, reasoning or review records, citation checks, cost logs, and metadata into a folder with a manifest and SHA-256 integrity hashes.

In plain words
What is it for?
Use it to prepare audit records for high-stakes legal deliverables, including their supporting review and citation-verification evidence.
Why use it?
Important AI-assisted work can be difficult to reconstruct later. A single record helps show which model, sources, checks, date, cost, and approver were involved.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Part of the fundament-weryfikacyjny plugin — 11 skills shipped together

Good fit Use it to prepare audit records for high-stakes legal deliverables, including their supporting review and citation-verification evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle
Install

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.

Any agent
npx skills add matematicsolutions/awesome-matematic-skills-pl --skill legal-ai-audit-bundle
Clone the repo
git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-pl

Made for: Claude Code.

Or install fundament-weryfikacyjny, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for legal-ai-audit-bundle

README.md
[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/legal-ai-audit-bundle)
Your own site
<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.

agentmods 80×15 button for legal-ai-audit-bundle

Your own site · 80×15
<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>
Per session 220 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00220 $0.03540
Opus 5 $0.00110 $0.01770
Sonnet 5 $0.00044 $0.00708
Haiku 4.5 $0.00022 $0.00354

Measured 12d ago against content hash 61f91854e7fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/assemble-bundle.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

fundament-weryfikacyjny/skills/legal-ai-audit-bundle/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

  1. 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).

  2. Opisz manifest - przygotuj descriptor JSON (patrz FORMAT) z metadanymi i ścieżkami do artefaktów.

  3. 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 + czytelny INDEX.md.

  4. Zweryfikuj kompletność - skrypt zwraca listę MISSING i ostrzega, jeśli brak record-keepingu wymaganego dla high-stakes. Uzupełnij albo świadomie odnotuj brak.

Read the full file on GitHub · 211 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 211 lines · 220 tokens per session scan A 61f91854e7fa

Subscribe to this mod's changes

legal-ai-audit-bundle is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. It adds 220 tokens to every session and 3,540 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

e-signature

Use when wiring an e-signature flow with DocuSign or Dropbox Sign — picking the SES/AES/QES legal tier, sending a PDF or template for signature, embedded signing, verifying signing webhooks, retrieving the signed PDF plus audit trail. NOT drafting contract text (that is contracts), NOT extracting fields from PDFs…

ericrisco/rsc-harness · 77 tokens

runtime-admissibility-review

Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI…

lawve-ai/awesome-legal-skills · 90 tokens

agent-authority-charter-builder-arkadiy-miteiko

Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…

lawve-ai/awesome-legal-skills · 85 tokens

metago-compliance

A pre-task checklist for checking legal, ethical, and security concerns before acting. It covers privacy, copyright, permissions, sensitive data, system safety, and regional compliance requirements.

metago-ai/metagolifeform · 62 tokens

metago-thought-19-negentropy-engine

A framework for assessing whether a system has a positive or negative effect on social order, information clarity, trust, fairness, and innovation. It uses changes in these areas to discuss social responsibility and ethical risk.

metago-ai/metagolifeform · 58 tokens

metago-security-engineer

Security Engineer - specializes in security audit, penetration testing, vulnerability management, compliance checking, security design review, supply chain security, and incident response.

metago-ai/metagolifeform · 34 tokens