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-goal)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-goal"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-goal/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-goal"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-goal.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 | $0.01199 |
| Opus 5 | $0.00015 | $0.00600 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
pg-imersao-goal 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/imersao:pg-imersao-goal — na sala, só refina
Na turma Founders AI este comando não constrói o app.
| Quando | O que fazer |
|---|---|
| Dia 2, montar o MVP | Pare. Mande /imersao:pg-imersao-implementar ou o Prompt 5 (/executing-plans). |
| Dia 3, depois da validação, com plano curto | Execute somente esse plano. Não refaça playbook, PRD, Design OS nem a onda 1. |
| Objetivo livre, fora da sala | Aí sim o motor completo (abaixo), com mapa de ondas. |
O caderno: caderno/Comece aqui.md. Prompt oficial do Dia 3: caderno/06-Prompts/Prompt 6 - Refinar.md.
Se $ARGUMENTS estiver vazio, pergunte: "Qual o plano curto de hoje — ou é um objetivo novo, fora da imersão?"
Se o argumento tem --plan ou um arquivo em docs/superpowers/plans/
Trate como refinamento da onda 1 já pronta:
- Leia o plano curto. Se ele pedir reconstruir MVP, brainstorming, PRD ou Design OS — pare e corte essas tarefas.
- Invoque
executing-planssó no que está no plano curto. - Regressão: fluxo principal, persistência, conexões, testes, tipos, build.
- Atualize
docs/o-que-e-real.md. - Resumo + roteiro de apresentação. Espere autorização antes de publicar.
Não invente onda 2 no meio. Onda 2 é depois, na mesma pasta, com o Guia 2.
Narração didática (turma de construtores de produto, não-devs)
- Automatize o encanamento (git, deps, comandos). O aluno não digita isso.
- Narre o CONCEITO em UMA linha, em português, na primeira vez.
- Nunca despeje jargão ou log cru sem traduzir.
| Conceito | Diga assim (1 linha, simples) |
|---|---|
| salvar versão (commit) | "Salvei um ponto do projeto que dá pra voltar depois, tipo um save de jogo." |
| teste | "Fiz um cheque automático que confirma que essa parte funciona — pra não quebrar sem você notar." |
| frontend / backend | "Frontend é o que você vê e clica; backend é o cérebro que processa e fala com o banco." |
| onda | "Onda 1 já está pronta. Agora a gente só corrige o que o uso mostrou — não começa o produto de novo." |
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 · 80 lines · 29 tokens per session scan A 97133953cba2
pg-imersao-goal is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 29 tokens to every session and 1,199 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 2026-08-31.
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.