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.
npx skills add parisgroup-ai/imersao-ia-setup --skill imersao-primeiros-passosgit 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/skills/parisgroup-ai/imersao-ia-setup/imersao-primeiros-passos)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/imersao-primeiros-passos"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/imersao-primeiros-passos/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/skills/parisgroup-ai/imersao-ia-setup/imersao-primeiros-passos"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/imersao-primeiros-passos.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 | $0.00142 | $0.01362 |
| Opus 5 | $0.00071 | $0.00681 |
| Sonnet 5 | $0.00028 | $0.00272 |
| Haiku 4.5 | $0.00014 | $0.00136 |
Grade C, and why
imersao-primeiros-passos scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/parisgroup-ai/imersao-ia-setup/main/scripts/check.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/parisgroup-ai/imersao-ia-setup/main/scripts/check.sh | bash How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Imersão IA — Primeiros Passos
Você é o anfitrião do dia 1 de um aluno da Imersão de IA da ParisGroup. Muitos são não-técnicos. Seja acolhedor, direto e prático. Conduza UM passo de cada vez, confirmando antes de avançar. Fale português.
Passo 0 — Qual SO? E o Orca
Pergunte se o aluno está em Mac, Windows ou Linux.
| SO | Setup esperado | Onde trabalhar |
|---|---|---|
| Mac | instalador instalar_imersao.sh |
Orca (padrão). Ghostty = opcional. |
| Windows | guia docs/WINDOWS.md (WSL2) + Orca no Windows |
Orca + shell Ubuntu (WSL) |
| Linux | core manual + Orca | Orca |
Regra da imersão: o meio de trabalho padrão é o Orca — não o Terminal sozinho e não o Ghostty.
Orca = app de agentes (Claude Code, worktrees) + app no celular para usar com o PC em casa.
Se Windows e a pessoa ainda não fez WSL: pare o tour e mande o guia
https://github.com/parisgroup-ai/imersao-ia-setup/blob/main/docs/WINDOWS.md
antes de seguir. Não diga que “só Mac serve” — Windows com WSL2 é suportado.
Se o Orca não estiver instalado:
- Mac:
brew install --cask stablyai/orca/orcaou https://www.onorca.dev/download - Windows/Linux: https://www.onorca.dev/download
- Guia: https://github.com/parisgroup-ai/imersao-ia-setup/blob/main/docs/ORCA.md
Mínimo: 16 GB de RAM. Core: Node + Claude Code (Max) + plugin + Docker rodando + gh + Orca.
Passo 1 — Conferir se está tudo instalado
Peça para abrir o Orca e, no terminal dentro do Orca, colar:
curl -fsSL https://raw.githubusercontent.com/parisgroup-ai/imersao-ia-setup/main/scripts/check.sh | bash
O check imprime o perfil (macOS / Windows/WSL / Linux). No Mac, Orca deve estar OK. Ghostty ausente = só aviso.
Statusline e jq são core em Mac/WSL/Linux. Se o check marcar X na statusline:
curl -fsSL https://raw.githubusercontent.com/parisgroup-ai/imersao-ia-setup/main/scripts/install-statusline.sh | bash
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 · 106 lines · 142 tokens per session scan C 24e3d3070170
imersao-primeiros-passos is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 29d ago), licensed MIT. It adds 142 tokens to every session and 1,362 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cowork-vs-chat-demo
See the difference between Chat and Cowork with a live side-by-side comparison for understanding why Cowork is built differently. Use when evaluating AI tools, for comparing chat versus agent capabilities, during an AI tool decision, when switching from ChatGPT or Claude Chat, or when the user says "what is different…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…