An offline tool for finding and replacing Polish personal data in text. It recognizes items such as PESEL, NIP, REGON, KRS, IBAN, names, email addresses, phone numbers, and addresses, then replaces them with tokens.

Use it to inspect documents for personal data, pseudonymize client files while keeping a recovery map, or permanently anonymize text before sharing it.

It lets you prepare documents without sending their contents to an AI model. It distinguishes between reporting, reversible pseudonymization, and irreversible anonymization so sensitive changes require the appropriate confirmation.

let-it-be — Skill for Claude Code by matematicsolutions

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 let-it-be

Clone the repo

git clone --depth 1 https://github.com/matematicsolutions/awesome-matematic-skills-pl

Made for: Claude Code.

Or install dokumenty, the plugin that ships this one along with the rest of its 10 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be/github.svg)](https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be)

Your own site

<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be"><img src="https://agentmods.dev/badge/skills/matematicsolutions/awesome-matematic-skills-pl/let-it-be.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,917 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.

Model	Per session	Once invoked
Fable 5.1	$0.00144	$0.01917
Opus 5	$0.00072	$0.00958
Sonnet 5	$0.00029	$0.00383
Haiku 4.5	$0.00014	$0.00192

Measured 11d ago against content hash b135c1c9a5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

let-it-be 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 11d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (bin/cli.mjs, src/audit-log.mjs, src/checksums.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.

dokumenty/skills/let-it-be/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Let It Be - anonimizacja danych po polsku

Samodzielny silnik (zero zaleznosci, Node >=20). Wykrywa polskie PII checksumowo (PESEL/NIP/REGON/KRS/IBAN/dowod osobisty), heurystycznie (imiona z gazetteera, firmy z forma prawna, e-mail, telefon, adres) i podmienia na tokeny. Dwa tryby RODO. Cala praca lokalnie.

Safety Tiers (KRYTYCZNE - dane osobowe)

Tier	Operacje	Regula
R - Read-only	`wykryj` (tylko raport, nic nie zmienia)	Bez potwierdzenia. Wykonaj od razu.
M - Mutating	`pseudonimizuj` + `odwroc`, `paczka` + `przywroc` (odwracalne przez mape/slownik)	Pokaz co zostanie zmienione. Czekaj na potwierdzenie slowne.
D - Destructive	`anonimizuj` (NIEODWRACALNE - mapa nie powstaje, danych nie przywrocisz)	Uzytkownik musi wpisac doslownie: "potwierdzam" zanim wykonasz.

Dotyczy zwlaszcza akt klientow i pism procesowych - anonimizuj na oryginale bez kopii = nieodwracalna utrata danych osobowych. Slownik *.mapa-pii.json zawiera oryginaly PII - chron go, nie wysylaj do LLM, nie commituj.

Quick start

Z katalogu skilla:

# Raport co jest w dokumencie (nic nie zmienia)
node bin/cli.mjs wykryj pismo.txt

# ANONIMIZACJA - nieodwracalna, do publikacji/dzielenia (brak mapy)
node bin/cli.mjs anonimizuj pismo.txt --out pismo-anon.txt

# PSEUDONIMIZACJA - odwracalna, do pracy z LLM (zapisuje mape)
node bin/cli.mjs pseudonimizuj pismo.txt --map mapa.json --out pismo-pseudo.txt
node bin/cli.mjs odwroc odpowiedz-llm.txt --map mapa.json   # przywraca oryginaly

# PACZKA - odwracalna redakcja WIELU plikow, jednolita numeracja (v0.2.0)
node bin/cli.mjs paczka pozew.txt zeznanie.txt --slownik sprawa.mapa-pii.json
node bin/cli.mjs przywroc odpowiedz-llm.txt --slownik sprawa.mapa-pii.json

Wejscie - lub brak = stdin. Wynik na stdout albo do --out.

Workflow: paczka dokumentow do LLM (v0.2.0)

Gdy sprawa sklada sie z kilku pism, paczka trzyma JEDEN slownik odwracania: ten sam byt w kazdym pliku = ten sam [OSOBA_1], liczniki nie resetuja sie per plik, a kolejne wywolanie z tym samym --slownik kontynuuje numeracje (takze po restarcie). przywroc podstawia oryginaly w odpowiedzi LLM lokalnie i ostrzega o placeholderach, ktorych slownik nie zna (zmyslone przez model).

Read the full file on GitHub · 113 lines

Files

What ships with it

21 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.

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.

11d ago First seen · 113 lines · 144 tokens per session scan A b135c1c9a5f7

Subscribe to this mod's changes

let-it-be is a skill published in the GitHub repository matematicsolutions/awesome-matematic-skills-pl (6 stars, last pushed 18d ago), licensed MIT. It adds 144 tokens to every session and 1,917 once invoked, about $0.0007 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.

Claude Code Legal and compliance Security agent-skills ai-act anti-hallucination audit-trail citation-grounding

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

let-it-be