Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-devnpx agentmods add skills/georgemarmelstein/superjurista-dev/capturar-sessao-pjeWrote 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/georgemarmelstein/superjurista-dev/capturar-sessao-pje)<a href="https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/capturar-sessao-pje"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/capturar-sessao-pje/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/georgemarmelstein/superjurista-dev/capturar-sessao-pje"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/capturar-sessao-pje.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 | $0.00029 | $0.02407 |
| Opus 5 | $0.00015 | $0.01203 |
| Sonnet 5 | $0.00006 | $0.00481 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade A, and why
capturar-sessao-pje 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.
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturar Sessao PJE
Descoberta Importante (2026-02)
O fluxo foi SIMPLIFICADO:
- Chrome autofill preenche CPF/senha automaticamente (credenciais salvas no navegador)
- JavaScript com
document.cookiecaptura TODOS os cookies necessarios, incluindoX-pje-cookies - NAO precisa mais de HAR - o metodo JavaScript e suficiente para listagem E download
Credenciais
As credenciais estao em .env na raiz do projeto (arquivo NAO versionado):
PJE_CPF=seu_cpf_aqui
PJE_SENHA=sua_senha_aqui
PJE_TOTP_SEED=seed_base32_do_google_authenticator
Para ler (se necessario preencher manualmente):
source .env 2>/dev/null || true
echo $PJE_CPF
2FA (Google Authenticator): desde a versao 2.11 do PJe (05/2026) o login exige
um codigo de 6 digitos do Google Authenticator. Esse codigo e um TOTP: e derivado
do seed em PJE_TOTP_SEED. Em vez de ler do celular, geramos por software (mesmo
seed = mesmo codigo). Ver Etapa 4.5. Se PJE_TOTP_SEED estiver vazio, o login para
no 2FA e o fallback e digitar manualmente o codigo do celular. Detalhes, como obter
o seed e solucao de problemas: references/2fa-totp.md.
Fluxo Principal (Chrome MCP)
Etapa 1: Verificar Chrome MCP
mcp__claude-in-chrome__tabs_context_mcp
Se Chrome MCP nao disponivel, ir para Metodo Fallback.
Etapa 2: Verificar aba PJE existente
Se ja houver aba com URL contendo pje1g.trf5.jus.br E QuadroAviso ou painel:
- Usuario JA esta logado
- Pular para Etapa 5 (captura de sessao)
Etapa 3: Criar aba e navegar
mcp__claude-in-chrome__tabs_create_mcp
mcp__claude-in-chrome__navigate -> https://pje1g.trf5.jus.br/pje/login.seam
mcp__claude-in-chrome__computer (action: wait, duration: 2)
What ships with it
3 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.
- 12d ago First seen · 270 lines · 29 tokens per session scan A ea33c127afae
capturar-sessao-pje is a skill published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,407 once invoked, about $0.0001 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 skills, from other repositories
policy-creation
Guide for adding new enterprise policies to Chromium. Complete guide for policy definitions, pref mapping, and writing tests.
privacy
Action-oriented guidelines for privacy by design, data minimization, third-party audits, and modern browser privacy APIs. Use this skill when dealing with user data, cookies, tracking, third-party scripts, or browser privacy APIs.
e-tax
A guide for entering Japanese tax-return data into the National Tax Agency's online tax-return preparation site, known as e-Tax, using browser automation.
legal-iros-registry-automation
A guide for helping automate bulk requests for company or property registry certificates from South Korea’s Supreme Court Internet Registry Office (IROS). The user handles login, authentication, and payment in the browser, while the workflow assists with collecting, saving, and reporting the documents.
browser-automation-expert
Drive a real browser to navigate, extract data and complete flows on sites without an API: scraping, crawling, authentication, dynamic content and anti-bot handling. Use when the user mentions web scraping, crawling, browser automation, Puppeteer or headless Chrome, wants data pulled from a website, needs a login or…
browse
Web browsing for legal work: extract contracts from portals, navigate legal research sites, pull documents from cloud storage, capture evidence screenshots.