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/joaoguirunas/team-osnpx agentmods add skills/joaoguirunas/team-os/sites-frontend-stackWrote 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/joaoguirunas/team-os/sites-frontend-stack)<a href="https://agentmods.dev/skills/joaoguirunas/team-os/sites-frontend-stack"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/sites-frontend-stack/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/joaoguirunas/team-os/sites-frontend-stack"><img src="https://agentmods.dev/badge/skills/joaoguirunas/team-os/sites-frontend-stack.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 | $0.00064 | $0.04146 |
| Opus 5.5 | $0.00026 | $0.01658 |
| Sonnet 5.5 | $0.00013 | $0.00829 |
| Haiku 4.5 | $0.00006 | $0.00415 |
Grade A, and why
sites-frontend-stack 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 1mo 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 — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sites Frontend Stack — Next.js e Astro + Tailwind v4 + shadcn/ui
Stack padrão das duas trilhas suportadas pela squad sites, estrutura de projeto, tokens de design (definidos UMA vez, compartilhados), padrões de componente em cada stack e composição shadcn/ui.
1. Escolha de stack
A decisão entre Next.js, Astro ou Híbrido é responsabilidade exclusiva do sites-architect (workflow "Escolher stack — Next.js / Astro / Híbrido", registrado como ADR em docs/smart-memory/decisions/ADR-{N}-stack-choice.md). Esta skill não repete os critérios de decisão — ela cobre a implementação de cada stack já decidida. Resumo de quando cada uma costuma entrar:
- Next.js — área autenticada complexa, painel com muito estado no cliente, infraestrutura de API pesada (webhooks, filas, jobs).
- Astro — site majoritariamente de conteúdo (institucional, landing page, blog, documentação, portfólio) com SEO/Core Web Vitals como prioridade dura.
- Híbrido (de ilha — um projeto Astro com ilhas React pontuais — ou separado — dois deploys, conteúdo em Astro e app autenticado em Next.js) — quando o projeto tem as duas necessidades ao mesmo tempo.
Ver o corpo do sites-architect para a tabela completa de critérios e o formato do ADR antes de escolher a stack de um projeto novo.
2. Stack Next.js
Next.js (App Router) + TypeScript
Tailwind CSS v4 (@theme CSS-first)
shadcn/ui (componentes base)
Motion — pacote `motion`, import de `motion/react` (ex-Framer Motion)
Lucide React (ícones)
next/font (tipografia)
Estrutura de projeto (Next.js)
src/
├── app/
│ ├── layout.tsx # Root layout
│ ├── page.tsx # Home
│ ├── globals.css # Tailwind + @theme (tokens)
│ └── [route]/
│ └── page.tsx
├── components/
│ ├── ui/ # shadcn components (nunca editar direto)
│ ├── sections/ # Seções de página (Hero, Features, CTA)
│ └── layout/ # Header, Footer
└── lib/
└── utils.ts # cn() e utilities
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.
- 1mo ago Changed 5bcc816c2154
- 1mo ago Changed · +200 lines · +3 tokens per session 88a067075200
- 2mo ago First seen · 194 lines · 61 tokens per session scan A 1647a18a424c
sites-frontend-stack is a skill published in the GitHub repository joaoguirunas/team-os (6 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 4,146 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-05.
sites-frontend-stack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sites-frontend-stackjoaoguirunas/team-os | Skill | 6 | 4d ago | MIT | A | 64 | Claude Code |
| ui-designmblode/agent-skills | Skill | 187 | yesterday | MIT | A | 86 | Claude Code, Codex |
| generic-react-design-systemtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 59 | Claude Code, Codex |
| claude-landing-composerOneWave-AI/claude-skills | Skill | 415 | 18d ago | MIT | A | 85 | Claude Code, Codex |
| artifacts-buildercomposio-community/awesome-claude-plugins | Skill | 2.0k | yesterday | none | A | 63 | Claude Code |
| frontend-designspytensor/openmozi | Skill | 441 | 3mo ago | MIT | A | 56 | Claude Code |
| dev-shadcnchristopherlouet/claude-base | Skill | 5 | 6d ago | MIT | A | 57 | Claude Code |