ekstraktor-cytatow-pl

ekstraktor-cytatow-pl is a skill for Claude Code from matematicsolutions/awesome-matematic-skills-pl. It costs 243 tokens per session (2,122 once invoked), scanned A, original, MIT.

A rule-based tool that finds and normalizes every legal reference in a Polish document, including case numbers, ECLI identifiers, official publication identifiers, and cited provisions. It also links short references such as “there” or “the judgment mentioned above” to the earlier citation.

In plain words
What is it for?
Use it to create a structured list of citations from a Polish legal document and pass that list to a separate source-verification step.
Why use it?
Citation checking can only cover references that were first found. Mechanical extraction reduces the risk of overlooking a citation or having a language model invent one.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

Good fit Use it to create a structured list of citations from a Polish legal document and pass that list to a separate source-verification step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl
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 ekstraktor-cytatow-pl
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 ekstraktor-cytatow-pl

README.md
[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl)
Your own site
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-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.

agentmods 80×15 button for ekstraktor-cytatow-pl

Your own site · 80×15
<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/ekstraktor-cytatow-pl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 243 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,122 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 $0.00243 $0.02122
Opus 5 $0.00121 $0.01061
Sonnet 5 $0.00049 $0.00424
Haiku 4.5 $0.00024 $0.00212

Measured 12d ago against content hash 4a0888a781f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ekstraktor-cytatow-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 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.

fundament-weryfikacyjny/skills/ekstraktor-cytatow-pl/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ekstraktor cytatów PL - znajdź każdy cytat, zanim go zweryfikujesz

Filozofia

Zweryfikować można tylko to, co się najpierw znajdzie. Grounding cytatu (citation-grounding-pl) sprawdza, czy dany cytat istnieje w źródle - ale działa na liście cytatów, którą ktoś musi najpierw zebrać. Ten skill jest tym front-endem: przechodzi pismo i wypisuje WSZYSTKIE odwołania, tak by żadne nie wymknęło się weryfikacji. Pominięty cytat to cytat niesprawdzony.

Ekstrakcja jest mechaniczna (wzorce + reguły, nie LLM) - to celowe: model na etapie znajdowania cytatów mógłby jeden przeoczyć albo dopowiedzieć. Lokalnie, RODO-safe.

Trzy kroki (za eyecite, zlokalizowane do PL)

  1. Ekstrakcja - rozpoznaj i wyłap każde odwołanie wg wzorców PL poniżej.
  2. Agregacja - rozwiąż odwołania skrótowe (tamże / op. cit. / wyżej powołany wyrok) do antecedentów wg reguł wrażliwych na wskaźnik (poniżej), żeby policzyć je jako jeden cytat, nie kilka.
  3. Przekazanie - oddaj ustrukturyzowaną listę do citation-grounding-pl do weryfikacji string-match.

Wzorce odwołań (PL)

Sygnatury orzeczeń

  • SN / sądy powszechne: izba rzymska + litera wydziału + numer/rok, np. II CSK NN/RR, I KZP NN/RR, III CZP NN/RR (NN = numer, RR = rok - placeholdery).
  • Sądy administracyjne: NSA II FSK NNNN/RR; WSA z oznaczeniem siedziby przez ukośnik, np. III SA/Wa NNN/RR, I SA/Gd NN/RR.
  • Trybunał Konstytucyjny: K 1/20, P 7/19, SK 3/18, Ts 45/20.
  • KIO (zamówienia publiczne): KIO NNN/RR, sprawy łączone KIO NNN/RR, KIO NNN/RR.
  • TSUE: C-123/20, odwoławcze C-123/20 P, sprawy połączone C-123/20 i C-124/20; Sąd UE T-456/19.

ECLI

  • Polski: ECLI:PL:SN:2015:IICSK24515, ECLI:PL:NSA:2018:....
  • Unijny: ECLI:EU:C:2020:559, ECLI:EU:T:2019:....

Akty prawne (Dz.U. / M.P. / ELI / UE)

  • Dz.U. RRRR poz. NNNN, Dz.U. z RRRR r. poz. NNNN, starszy format Dz.U. z RRRR r. Nr N, poz. NNNN.
  • M.P. 2019 poz. 50; Dz.Urz. UE L 119 (RODO), Dz.Urz. UE C ....
  • ELI URI Sejmu, np. .../DU/2020/1234.

Read the full file on GitHub · 116 lines

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 · 116 lines · 243 tokens per session scan A 4a0888a781f5

Subscribe to this mod's changes

ekstraktor-cytatow-pl is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 19d ago), licensed MIT. It adds 243 tokens to every session and 2,122 once invoked, about $0.0012 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