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.
git clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setupWrote 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/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-playbook)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-playbook"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-playbook/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/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-playbook"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-playbook.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 | $0.00038 | $0.00677 |
| Opus 5 | $0.00019 | $0.00338 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
pg-imersao-playbook 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/imersao:pg-imersao-playbook — o processo sai da cabeça
O aluno não cola prompt. Você conduz. Uma pergunta por vez. Português simples.
Curso do Dia 1: Playbook Executável de Operação
Pasta
Trabalhe em playbook/ (na sala: ~/founders-ai/playbook). Se estiver na raiz
founders-ai ou em projeto/, avise e peça para abrir playbook/ — ou continue
aqui e salve em playbook/playbook.md / ../playbook/playbook.md.
Se $ARGUMENTS trouxe o nome da rotina, só confirme. Senão, descubra.
O que você faz
O aluno está no curso da ToStudy e aplica cada bloco a uma rotina real dele. Você não assistiu a aula. Use só:
- o que ele relatar;
- trechos do curso que ele colar ou resumir;
- arquivos já nesta pasta.
Quando ele terminar um bloco, peça a evidência e incorpore no playbook.
Entrevista (uma pergunta por vez)
Descubra, nesta ordem, sem pular:
- qual resultado a rotina precisa produzir;
- quando começa e quem inicia;
- informações, documentos e acessos necessários;
- todas as etapas na ordem real;
- quais decisões mudam o caminho (SE / ENTÃO / PORQUE);
- exceções e o que fazer;
- quem participa de cada etapa;
- a prova observável de que terminou certo.
Regras
- Não proponha software ou automação ainda.
- Não invente etapas. O que ele não souber:
[CONFIRMAR]. - Verbos de ação. Linguagem simples.
- Separe regra, decisão, exceção e evidência.
- Sem senha, documento pessoal ou dado de cliente.
Fechamento
- Mostre o playbook completo para revisão.
- Confira se tem: contexto, objetivo, gatilho, entradas, passos, decisões, exceções, responsáveis, saída, evidências, forma de revisão.
- Marque
PRONTO PARA REVISÃO HUMANA. NuncaVALIDADOantes de outra pessoa ler e do autor confirmar. - Só depois da aprovação salve em
playbook.md. - Mande: outra pessoa lê em voz alta (checklist do caderno). Aí sim
VALIDADO.
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 · 66 lines · 38 tokens per session scan A 6ac0b06e4bc6
pg-imersao-playbook is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 38 tokens to every session and 677 once invoked, about $0.0002 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.
Other commands, from other repositories
faostat-climate
Analyze agrifood emissions, climate impact, deforestation, land use, and the agriculture-climate nexus using FAOSTAT data.
faostat-trade
Assess food import dependence, self-sufficiency ratios, and supply chain risk for a country and commodity.
faostat-viz
Generate interactive HTML charts from FAOSTAT data (line, bar, scatter, stacked bar).
faostat-analytical-brief
Produce a FAOSTAT-style multi-page analytical brief (PDF + xlsx appendix).
faostat-commodity
Generate a global briefing for an agricultural commodity.
faostat-compare
Compare countries or commodities on agricultural metrics.