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/parisgroup-ai/imersao-ia-setupnpx agentmods add commands/parisgroup-ai/imersao-ia-setup/pg-imersao-startWrote 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-start)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-start"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-start/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-start"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-start.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 | $0.00034 | $0.01524 |
| Opus 5 | $0.00017 | $0.00762 |
| Sonnet 5 | $0.00007 | $0.00305 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
pg-imersao-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/imersao:pg-imersao-start — a bússola da imersão
Você é uma bússola, não um piloto automático. Oriente: mostre o mapa da sala, diga onde o aluno está e qual o próximo passo — NUNCA execute as fases sozinho. Quem roda cada passo é o aluno.
Fale 100% em português simples.
Se o aluno estiver perdido, aponte o Caderno Founders:
caderno/Comece aqui.md (no repo da imersão). É o manual. Não é o vault da empresa.
1. Descubra onde o aluno está (checks por baixo dos panos)
Aceite as duas árvores: a da sala (~/founders-ai/projeto) e a do atalho
(docs/plano-do-produto.md na pasta atual).
APP="$(basename "$PWD")"; DESIGN_DIR="../${APP}-design"
# Plano da sala (PRD) OU do atalho (plano-do-produto)
{ [ -f docs/PRD.md ] || [ -f docs/plano-do-produto.md ] || [ -f ../projeto/docs/PRD.md ]; } && echo "PLANO=sim" || echo "PLANO=nao"
[ -f playbook/playbook.md ] || [ -f ../playbook/playbook.md ] && echo "PLAYBOOK=sim" || echo "PLAYBOOK=nao"
{ [ -f "$DESIGN_DIR/product-plan.zip" ] || [ -d "$DESIGN_DIR/product-plan" ] || [ -d product-plan ] || [ -d ../projeto/product-plan ]; } && echo "EXPORT=sim" || echo "EXPORT=nao"
{ [ -f package.json ] && grep -q '"next"' package.json 2>/dev/null; } && echo "APP=sim" || echo "APP=nao"
git remote get-url origin >/dev/null 2>&1 && echo "PUBLICADO=sim" || echo "PUBLICADO=nao"
Se a pasta terminar em -design e não for projeto-design da sala: avise
que a bússola roda na pasta do app e pare.
Se estiver em ~/founders-ai (raiz), oriente: playbook em playbook/, Claude
do produto em projeto/.
2. Mostre SEMPRE o mapa da sala (marque onde ele está com ➜)
🗺️ Sua jornada — o método da sala (3 dias):
Dia 1 CONTEXTO curso + playbook + produto com mapa de ondas
Dia 2 GERAÇÃO protótipo + plano + onda 1 (MVP) funcionando
Dia 3 ENTREGA validar + refinar + apresentar + publicar
A onda 1 é o primeiro andar. O prédio que você imaginou continua no plano.
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 · 91 lines · 34 tokens per session scan A a52c38465063
pg-imersao-start is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,524 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
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
pattern
Show solution pattern cards from course-index/patterns.md, filtered by topic or keyword.
code-explainer
Use when a designer needs to understand code that already works. What a file does, what a line means, which parts are safe to change. Plain language with Figma analogies, no developer jargon.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
hwmap
Show HW/example coverage of course sections from course-index/coverage.md. HW density = exam probability; surface the exam-hot zones.
help
Interactive getting-started tutorial for your first Z specification.