Borrowing it
Nothing to install: this file belongs to marcosmarf27/tecjustica-sigilo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcosmarf27/tecjustica-sigilo/main/CLAUDE.mdgit clone --depth 1 https://github.com/marcosmarf27/tecjustica-sigiloWrote 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/instructions/marcosmarf27/tecjustica-sigilo/claude-md)<a href="https://agentmods.dev/instructions/marcosmarf27/tecjustica-sigilo/claude-md"><img src="https://agentmods.dev/badge/instructions/marcosmarf27/tecjustica-sigilo/claude-md/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/instructions/marcosmarf27/tecjustica-sigilo/claude-md"><img src="https://agentmods.dev/badge/instructions/marcosmarf27/tecjustica-sigilo/claude-md.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 | $0.20016 | $0.20016 |
| Opus 5 | $0.10008 | $0.10008 |
| Sonnet 5 | $0.04003 | $0.04003 |
| Haiku 4.5 | $0.02002 | $0.02002 |
Grade A, and why
tecjustica-sigilo CLAUDE.md 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 2d 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 — 1,228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TecJustiça Sigilo — o que não está óbvio no código
Anonimizador de dados pessoais em processos judiciais brasileiros. Electron + React + FastAPI + Presidio. Tudo roda na máquina do usuário: nenhuma página sai daqui.
O Presidio deixou de ser da Microsoft e virou projeto comunitário sob a Data Privacy Stack (licença MIT). Pacotes no PyPI e API continuam iguais, e o projeto o usa em processo — não há Docker aqui, então a mudança de registro (
mcr.microsoft.com→ghcr.io/data-privacy-stack) não afeta nada. Documentação:presidio.dataprivacystack.org.
Este arquivo guarda o que custou caro descobrir. O resto está no código.
Onde desenvolver
No Windows. É um aplicativo Windows e pelo WSL as medições que importam
ficam distorcidas: o python.exe embarcado lido pela ponte \\wsl.localhost
leva 20 s para carregar 31 MB de modelo (menos de 2 s no disco local) e mais de
2 minutos para importar o torch (~12 s local). Guia:
docs/desenvolvimento-windows.md.
Rodar a suíte não é a mesma coisa que abrir o app. Os dois bugs mais graves de agosto/2026 passaram por 110 testes verdes e só apareceram quando o usuário instalou e usou. Antes de dizer que está pronto: abrir o app.
O que não está no git e cada máquina precisa obter
| Como | |
|---|---|
resources/ocr-models/*.onnx (163 MB) |
scripts/fetch-ocr-models.sh |
resources/python-backend/python-embed/ (1,8 GB) |
scripts/setup-python-embed.sh |
.venv/ |
pip install -r python-backend/requirements.txt |
| BERT (~433 MB) | baixa sozinho na primeira execução, em ~/.cache/huggingface — revisão pinada por SHA em engine.py |
| Corpus de OCR (22 PDFs reais, 125 MB) | não está em repositório nenhum — copiar entre máquinas à mão |
| Corpus de acurácia (3 processos do TJCE em markdown, 1,6 MB) | idem — são os documentos do gate |
Os dois corpora carregam dados pessoais reais, por isso ficam fora do git, e cada um é apontado por uma variável:
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.
- 2d ago Changed · +101 lines · +1,765 tokens per session 27df0870347f
- 4d ago Changed · +185 lines · +3,216 tokens per session 30908a2c7c7c
- 6d ago Changed · +635 lines · +10,230 tokens per session efd66ab1d72c
- 10d ago First seen · 307 lines · 4,805 tokens per session scan A 689b322bea33
tecjustica-sigilo CLAUDE.md is an instructions file published in the GitHub repository marcosmarf27/tecjustica-sigilo (25 stars, last pushed 3d ago), licensed MIT. It adds 20,016 tokens to every session, about $0.1001 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.