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-publicar)<a href="https://agentmods.dev/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-publicar"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-publicar/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-publicar"><img src="https://agentmods.dev/badge/commands/parisgroup-ai/imersao-ia-setup/pg-imersao-publicar.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 | $0.00026 | $0.02385 |
| Opus 5 | $0.00013 | $0.01192 |
| Sonnet 5 | $0.00005 | $0.00477 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
pg-imersao-publicar 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/imersao:pg-imersao-publicar — Fase 4: colocar o app no ar
O app já roda no seu computador. Agora vamos colocar ele no ar — num link que qualquer pessoa abre no navegador. São duas partes: guardar o código no GitHub e publicar no Railway (que roda o app e o banco na nuvem, lendo do seu GitHub).
Por que isso existe (diga em voz de dono, 3 linhas):
- Prova — o produto saiu da cabeça e ganhou endereço.
- Uso — sem URL, ninguém de fora testa; o plano de 30 dias não tem usuário de verdade.
- Manutenção — a onda 2 não pede “instala de novo no meu PC”.
git pushatualiza o mesmo link.
GitHub é o cartório. Railway é a loja. Push é a reposição. Detalhe no caderno:
caderno/05-Guias/Por que publicar.md.
Narração didática (Fase 4)
Automatize a mecânica, narre o conceito em 1 linha na primeira vez (nunca a sintaxe):
| Conceito | Diga assim |
|---|---|
| GitHub | "O GitHub é onde seu código fica guardado na nuvem, com histórico — tipo um Drive do programador." |
| deploy / no ar | "Publicar (deploy) é colocar seu app num link público, pra qualquer um abrir — não fica só no seu computador." |
| Railway | "O Railway é um serviço que roda seu app e seu banco na nuvem 24h, a partir do seu GitHub." |
| variável de ambiente | "Uma 'configuração secreta' (tipo o endereço do banco) que fica fora do código e muda em cada lugar." |
| registro de honestidade | "É um arquivo no seu projeto (docs/o-que-e-real.md) que anota o que funciona de verdade e o que está em demonstração — a gente confere ele antes de publicar." |
Pré-condições
- Trabalhe na pasta do app (a mesma do
docs/PRD.mdoudocs/plano-do-produto.md), com o app já construído (tempackage.jsoncomnext). Na sala:~/founders-ai/projeto. - O app precisa buildar pra produção. Rode silenciosamente; se falhar, conserte antes
de seguir (narre em português, não mostre log cru):
npm run build - As migrations do Drizzle precisam estar commitadas (a Fase 3 já commita) — é o que cria as tabelas no banco da nuvem no deploy.
- O script
starttem que ser onext startpadrão (não fixe a porta com-p 3000) — o Railway injeta a porta sozinho e onext starta respeita.
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 · 143 lines · 26 tokens per session scan A 337a5ca2fd3a
pg-imersao-publicar is a command published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,385 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
gitops
Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised…
ship-deployment
This file contains platform-specific deployment and validation for /ship.
spec-release
Generate release notes, changelog, and deployment checklist.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
fluxcd
FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.