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 adversarial-legal-review-plgit 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/adversarial-legal-review-pl)<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/adversarial-legal-review-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/adversarial-legal-review-pl/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/adversarial-legal-review-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/adversarial-legal-review-pl.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 | $0.00268 | $0.07579 |
| Opus 5.5 | $0.00107 | $0.03032 |
| Sonnet 5.5 | $0.00054 | $0.01516 |
| Haiku 4.5 | $0.00027 | $0.00758 |
Grade A, and why
adversarial-legal-review-pl 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Legal Review PL - czerwony zespół dla pisma prawnego
Filozofia
Lepiej, żeby słabość Twojej tezy znalazł Twój własny agent niż przeciwnik na rozprawie.
Pojedynczy przebieg LLM produkuje argumentację, która brzmi pewnie - bo model jest trenowany, by brzmieć pewnie. To złudzenie kompetencji. Prawdziwa wartość prawnika to przewidzieć kontrargument, kontr-orzecznictwo i lukę w rozumowaniu, zanim zrobi to druga strona. Ten skill instytucjonalizuje kontradyktoryjność: jeden agent broni, drugi atakuje, trzeci godzi, czwarty weryfikuje.
To NIE jest pisanie deliverable od zera. To stress-test gotowego deliverable.
Bramka kosztu (czytaj PRZED uruchomieniem)
Pełny cykl jest drogi tokenowo. Uruchamiaj tylko dla wysokiej stawki:
| Uruchom (high-stakes) | NIE uruchamiaj (zwykłe) |
|---|---|
| Opinia prawna do klienta | Notatka wewnętrzna |
| Due diligence / memo M&A | Streszczenie orzeczenia |
| Pismo procesowe przed terminem | Robocza analiza, draft |
| Rekomendacja do zarządu kancelarii | FAQ, content marketingowy |
| Stanowisko niosące istotne ryzyko finansowe lub reputacyjne | Zapytanie rutynowe |
Jeśli sprawa nie jest high-stakes - powiedz to wprost i zaproponuj zwykły jednoprzebiegowy review zamiast pełnej debaty. Nie pal tokenów na rutynę.
Workflow (4 role + weryfikacja)
Każda rola to osobny przebieg z czystym mandatem. Pseudonimizuj wejście przez let-it-be,
jeśli dokument zawiera dane objęte tajemnicą zawodową.
Poziomy dostępu recenzentów (anty-bias)
Recenzenci dzielą się na dwa poziomy o RÓŻNYM dostępie do materiału. To jest celowe, nie przypadkowe:
- IZOLOWANY (spójność wewnętrzna): recenzent logiki i struktury widzi wyłącznie bieżący draft - bez źródeł, bez orzecznictwa. Mandat: czy teza nie przeczy własnemu uzasadnieniu, czy wnioski wynikają z przesłanek, gdzie są luki logiczne. NIE ocenia, czy cytat jest prawdziwy. Gdyby widział źródła, myliłby „brzmi jak źródło" z „jest spójne wewnętrznie".
- WZBOGACONY (grounding): attacker (rola 2) i kontrola cytatów (punkt 1 verifiera) widzą źródła i intake, i sięgają po orzecznictwo przeciwne. Mandat: oparcie twierdzeń i autorytet przeciwny.
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 a21b9fab689f
- 1mo ago First seen · 372 lines · 268 tokens per session scan A 2858449b6f01
adversarial-legal-review-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (8 stars, last pushed 8d ago), licensed MIT. It adds 268 tokens to every session and 7,579 once invoked, about $0.0011 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.