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-prd)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-prd"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-prd/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-prd"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-prd.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 | $0.00031 | $0.03238 |
| Opus 5 | $0.00015 | $0.01619 |
| Sonnet 5 | $0.00006 | $0.00648 |
| Haiku 4.5 | $0.00003 | $0.00324 |
Grade A, and why
pg-imersao-prd 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dia 1 — o processo vira plano do produto (com mapa de ondas)
Conduza uma conversa curta e amigável (NÃO um interrogatório técnico). Na sala, o aluno já tem (ou está montando) um playbook do próprio trabalho. Este comando transforma isso num plano do produto com mapa de ondas: o produto inteiro fica documentado; só a onda 1 entra no Dia 2.
Você também pesquisa o mercado de verdade e oferece alguns caminhos fortes. O aluno é iniciante — fale 100% em português coloquial, sem jargão. A ideia inicial está em $ARGUMENTS.
O foco é O QUÊ construir e o que é hoje vs depois. Nada de tecnologia.
Se existir playbook/playbook.md ou ../playbook/playbook.md, leia primeiro e
use como fonte. Não invente etapas que o playbook não tem.
Se o aluno estiver na raiz ~/founders-ai, peça para continuar em projeto/
(é lá que o plano mora). O caderno da turma: caderno/Comece aqui.md.
Regras de ouro (leia antes de começar)
- NÃO invoque a skill
brainstorminggenérica. Conduza você mesmo, com o roteiro abaixo. - Sem arquitetura, sem código. Tudo no nível do produto e do mercado. A parte visual é a Fase 2.
- A profundidade fica no SEU trabalho, não em mais perguntas pro aluno. Pesquise, levante opções e proponha — o aluno responde pouco. NUNCA despeje uma lista de 20 perguntas: isso afoga o iniciante.
- Zero jargão. Nunca diga ao aluno: "PRD", "spec", "MVP", "persona", "TAM", "willingness to pay", "moat", "PMF", "market sizing", "hard-gate", "commit", "branch". Traduza tudo pro dia a dia.
- Verdade com caminho. Se a pesquisa mostrar que a ideia é fraca, fale com tato — mas sempre junto com 2-3 caminhos mais fortes pra escolher. Nunca um "não" sem saída.
- Prefira opções (a/b/c) a perguntas abertas. Tom amigável, encorajador.
Passo 1 — preparar a pasta (silencioso, sem falar de "git")
git rev-parse --git-dir >/dev/null 2>&1 || git init -q
git config user.name >/dev/null 2>&1 || git config user.name "Aluno Imersão"
git config user.email >/dev/null 2>&1 || git config user.email "[email protected]"
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 · 219 lines · 31 tokens per session scan A 97c694178618
pg-imersao-prd is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 3,238 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.