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 ThomasMoreAI/legal-skills-open --skill pii-scrubgit clone --depth 1 https://github.com/ThomasMoreAI/legal-skills-openWrote 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/thomasmoreai/legal-skills-open/pii-scrub)<a href="https://agentmods.dev/skills/thomasmoreai/legal-skills-open/pii-scrub"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pii-scrub/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/thomasmoreai/legal-skills-open/pii-scrub"><img src="https://agentmods.dev/badge/skills/thomasmoreai/legal-skills-open/pii-scrub.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 | $0.00125 | $0.02853 |
| Opus 5.5 | $0.00050 | $0.01141 |
| Sonnet 5.5 | $0.00025 | $0.00571 |
| Haiku 4.5 | $0.00013 | $0.00285 |
Grade A, and why
pii-scrub 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 24d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pii-scrub
Purpose
Before a lawyer pastes processual content, client data, or contracts into Claude, pseudonymize sensitive identifiers. This skill:
- Scrubs the text — names → PARTE_A/PARTE_B, CPF/CNPJ/RG → [REDIGIDO], phone/email/address → [REDIGIDO], processo numbers → [Nº PROCESSO]
- Returns a local de-para table — maps scrubbed IDs back to real values so you can re-identify results later
- Flags legal risks — asks about segredo de justiça and LGPD art. 11 dados sensíveis before you paste
Jurisdição & Base Legal (Brasil)
This skill assumes Brasil (LGPD, Lei 13.709/2018) as the default jurisdiction. The obligations around PII and dados sensíveis come from:
- Lei 13.709/2018 (LGPD) — art. 7 (base legal for treatment), art. 11 (dados sensíveis: health, race/ethnicity, political opinion, religious belief, union membership, genetic, biometric data), art. 48 (notification to ANPD upon incident), art. 41 (DPO obligations)
- CPC (Código de Processo Civil) — art. 189 (segredo de justiça — interesse público/social, família, dados íntimos e arbitragem confidencial podem tramitar em segredo; sucessões ou mediação não aparecem como categorias gerais autônomas)
[verified: https://www.planalto.gov.br/ccivil_03/_ato2015-2018/2015/lei/l13105.htm] - Lei 12.527/2011 (Lei de Acesso à Informação) — art. 31 (personal data excluded from disclosure requirements unless subject consented)
Load context
~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md → your privacy practice profile (DPA status, regulatory footprint, base legal for data handling by the assistant).
Workflow
Step 1: Ask about legal classification
Before scrubbing, ask:
Quick legal check — answer 1-2 questions:
- Does this document run under segredo de justiça (CPC art. 189
[verified: https://www.planalto.gov.br/ccivil_03/_ato2015-2018/2015/lei/l13105.htm]) or involve a sealed/confidential proceeding? (Yes / No / Unsure)- Does it contain dados sensíveis (health, race/ethnicity, religion, political opinion, biometrics, union, genetic — LGPD art. 11
[verified: https://www.planalto.gov.br/ccivil_03/_ato2015-2018/2018/lei/l13709.htm])? (Yes / No / Unsure)If yes to either: caution flag (see Step 4 below) before scrubbing.
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.
- 24d ago First seen · 196 lines · 125 tokens per session scan A 1aedf2462b62
pii-scrub is a skill published in the GitHub repository ThomasMoreAI/legal-skills-open (95 stars, last pushed 15d ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,853 once invoked, about $0.0005 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 2026-10-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…