criar-pje-download

criar-pje-download is a skill for Claude Code from georgemarmelstein/superjurista-dev. It costs 74 tokens per session (3,935 once invoked), scanned A, original, MIT.

Uma ferramenta para criar adaptações do PJe Download para diferentes tribunais. Ela usa um arquivo HAR, que registra as comunicações do navegador com o site, para descobrir os dados necessários.

In plain words
What is it for?
Serve para criar uma skill de download para um novo tribunal, analisar um arquivo HAR e gerar um bookmarklet e scripts de apoio.
Why use it?
Cada tribunal pode configurar o PJe de forma diferente, o que impede que um único download funcione em todos eles. A ferramenta ajuda a adaptar o processo ao tribunal escolhido.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/extrair_cookies_har.py --har ~/Downloads/pje.har --output session.json.

Part of the superjurista-dev plugin — 11 skills, 22 commands, 7 agents shipped together

Good fit Serve para criar uma skill de download para um novo tribunal, analisar um arquivo HAR e gerar um bookmarklet e scripts de apoio.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev
agentmods
npx agentmods add skills/georgemarmelstein/superjurista-dev/criar-pje-download

Made for: Claude Code.

Or install superjurista-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 7 agents.

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 criar-pje-download

README.md
[![agentmods](https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-pje-download/github.svg)](https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-pje-download)
Your own site
<a href="https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-pje-download"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-pje-download/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 criar-pje-download

Your own site · 80×15
<a href="https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-pje-download"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-pje-download.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,935 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 $0.00074 $0.03935
Opus 5 $0.00037 $0.01968
Sonnet 5 $0.00015 $0.00787
Haiku 4.5 $0.00007 $0.00394

Measured 12d ago against content hash c2972dbfc317, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

criar-pje-download 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.

skills/criar-pje-download/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Criar Skill PJE Download

<quando_usar> - Usuario quer baixar processos de tribunal diferente do TRF5 - Usuario menciona "criar skill para [tribunal]" - Usuario tem arquivo HAR ou quer usar bookmarklet de outro tribunal - Usuario quer adaptar pje-download para seu tribunal - Se o tribunal for TRF5, usar skill pje-download diretamente - Se usuario so quer baixar (nao criar skill), usar skill existente </quando_usar>

**Como funciona:**
O PJE injeta `window.PJe.CONSTANTES` na pagina com valores especificos do
tribunal (app name, localizacao, instancia). O bookmarklet le esses valores
em tempo de execucao, tornando-o automaticamente adaptavel. Em tribunais mais
antigos ou sem esse objeto, usa valores de fallback ou pergunta ao usuario.

**Template parametrizado:**
Consultar `references/template-bookmarklet.md` para o template completo com
placeholders `{{PJE_APP_NAME}}`, `{{TRIBUNAL_ID}}` e `{{LOCALIZACAO_DEFAULT}}`.

**Gerar o bookmarklet** no Passo 7 junto com os scripts Python.

**Formato do sessao.json:**
O bookmarklet produz um JSON com campos comuns (`cookies`, `headers_api`,
`cookie_download`, `base_url`, `extraido_em`, `metodo`). Este formato NAO e
um contrato rigido. O agente que cria a skill para um novo tribunal deve:
1. Verificar o que os scripts Python realmente consomem (via Read nos scripts)
2. Adaptar o bookmarklet para produzir exatamente os campos necessarios
3. Documentar o formato esperado no SKILL.md da skill gerada

O template em `references/template-bookmarklet.md` e um ponto de partida
que cobre a maioria dos tribunais PJE 2.x.

**Quando o bookmarklet NAO funciona:**
- Cookies HttpOnly: `document.cookie` retorna string vazia/incompleta
- CSP bloqueando inline JS: bookmarklet nao executa
- Tribunal usa autenticacao diferente do padrao PJE

Nesses casos, ir para Passo 1 (HAR).
**HAR de Listagem (obrigatorio):**
```
1. Abra o PJE do seu tribunal no navegador
2. Faca login com certificado digital
3. Abra DevTools (F12) -> aba Network
4. Marque "Preserve log" para nao perder requisicoes
5. Navegue ate o Painel do Usuario
6. Aguarde carregar a lista de processos
7. Clique direito na lista -> "Save all as HAR"
8. Salve como: pje_listagem.har
```

**HAR de Download (recomendado):**
```
1. Com DevTools ainda aberto
2. Clique em um processo da lista
3. Solicite download dos autos digitais
4. Aguarde o PDF comecar a baixar
5. Salve novo HAR: pje_download.har
```

Read the full file on GitHub · 366 lines

Files

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.

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 · 366 lines · 0 tokens per session scan A c2972dbfc317

Subscribe to this mod's changes

criar-pje-download is a skill published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 3,935 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens