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-implementarWrote 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-implementar)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-implementar"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-implementar/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-implementar"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-implementar.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 | $0.00037 | $0.03916 |
| Opus 5 | $0.00018 | $0.01958 |
| Sonnet 5 | $0.00007 | $0.00783 |
| Haiku 4.5 | $0.00004 | $0.00392 |
Grade A, and why
pg-imersao-implementar 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/imersao:pg-imersao-implementar — Dia 2: export + plano → onda 1 funcionando
Você vai construir a onda 1 (o MVP de hoje), a partir do protótipo exportado e do
plano (docs/PRD.md ou docs/plano-do-produto.md), na stack pública da imersão.
Não use /imersao:pg-imersao-goal para construir. Goal na sala é só no Dia 3, para
refinar. Aqui: tabela de ondas → /writing-plans → /executing-plans só da onda 1.
E "de verdade" quer dizer de verdade: nada de funcionalidade fingida sem avisar. O que
depender de serviço de fora (IA, pagamento, e-mail…) é real ou demonstração explícita
— e o aluno decide isso ANTES de você construir (item 3).
Narração didática (construir, mas o aluno entende a lógica)
Esta fase tem a mecânica mais técnica (banco, migration, testes). Siga a regra da imersão: automatize a mecânica, narre o conceito em 1 linha. Aqui vão os conceitos específicos desta fase — explique cada um na primeira vez que aparecer, em português simples (nunca narre a sintaxe/flags, só o o quê e o porquê):
| Conceito | Diga assim (1 linha) |
|---|---|
| app = 3 partes | "Todo app tem 3 partes: a tela (o que você vê), o cérebro (a lógica) e o banco (onde guarda os dados). Vou montar as três." |
| banco de dados | "O banco é onde as informações do app ficam guardadas — tipo uma planilha gigante que o app lê e escreve." |
| migration | "Uma migration é como o app cria as 'gavetas' do banco (as tabelas). Toda mudança no formato dos dados vira uma migration." |
| Docker | "O Docker é uma caixinha que roda o banco no seu computador sem você instalar nada à mão." |
| rodar local | "Seu app está rodando só no seu computador (localhost) por enquanto — depois dá pra colocar no ar pra outros acessarem." |
| chave de API | "A chave de API é a 'senha' que deixa seu app usar a IA — ela é separada da sua assinatura do Claude e custa centavos por uso (você só paga o que o app consumir)." |
| modo demonstração | "No modo demonstração o app mostra respostas de exemplo, claramente marcadas com um selo, até você colocar a chave de verdade — aí vira real sozinho." |
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 · 238 lines · 37 tokens per session scan A aecba4dd196a
pg-imersao-implementar is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 37 tokens to every session and 3,916 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
octo-schedule
Manage scheduled workflow jobs for the Claude Octopus scheduler.
octo-scheduler
Manage the Claude Octopus scheduled workflow runner daemon.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
next
Read the active sprint’s current status. Refresh stale compilation using grainulator compile --dir or grainulator.compile. Use the resulting nextactions with the user’s current scope and authorization. Output only the two Auto and Manual lists below, with no recap, status counters or offer to continue. Continue useful…
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.