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 andregusman-raiz/a-gusman-claude --skill ag-referencia-prompt-guidegit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-referencia-prompt-guide)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-prompt-guide"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-prompt-guide/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/andregusman-raiz/a-gusman-claude/ag-referencia-prompt-guide"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-prompt-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.02861 |
| Opus 5.5 | $0.00023 | $0.01144 |
| Sonnet 5.5 | $0.00012 | $0.00572 |
| Haiku 4.5 | $0.00006 | $0.00286 |
Grade A, and why
ag-referencia-prompt-guide 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Guide — Gerar UI via AI
Inspirado em GlowUp UI (glowupui.io) e validado com o design-library rAIz. Complementa
/ag-referencia-design-presentation(taxonomia de 86 layouts). Uso: antes de qualquer geração de UI via Claude/Cursor/Lovable/v0.
Princípio
Builder AI gera o que você descreve, não o que você quer. Prompt fraco = 5-15 iterações queimando créditos. Prompt estruturado = 1-2 shots para resultado utilizável.
A diferença entre um prompt que queima tempo e um que acerta está em quantos tipos de informação ele carrega, não em quão longo é.
Estrutura canônica — 6 blocos
Todo prompt de UI bom tem estes 6 blocos (nesta ordem):
1. Contexto → quem usa, para quê, em que produto
2. Layout base → qual a estrutura geométrica pretendida
3. Estilo → identidade visual + tokens (cores, radius, tipografia, spacing)
4. Referências → screenshots, URLs de inspiração, ID de variante do design-library
5. Constraints → stack, dependências permitidas, tamanho, a11y, mobile
6. Entregável → formato (1 arquivo? múltiplos? spec markdown? prompt otimizado?)
Skippar qualquer bloco = AI inventa. Exceção: Referências é opcional se o layout é simples ou se #1 e #2 já são precisos.
Template mestre
Copiar e preencher placeholders:
# Build: <NOME CURTO DO COMPONENTE>
## Contexto
Você é um designer senior implementando uma seção de <CATEGORIA> para <TIPO DE PRODUTO>.
Usuário final: <PERSONA>. Objetivo: <O QUE O USUÁRIO DEVE FAZER/SENTIR>.
## Layout base
<DESCRIÇÃO ESTRUTURAL EM 1-2 FRASES — ex: "layout 50/50 desktop, stack mobile, form à esquerda, visual à direita">
## Estilo (design tokens)
- Cor primária: <HEX + nome CSS var>
- Cor secundária: <HEX + nome CSS var>
- Radius: <VALOR> (ex: 0.75rem = rounded-xl)
- Typography: <FONT FAMILY + TRACKING>
- Dark mode: <class strategy | data-attribute | nenhum>
- Spacing: <8pt grid | 4pt grid | custom>
- Shadows: <subtle | pronounced | nenhum>
- Motion: <none | subtle — 150-250ms ease-out, sem transition:all, sem ease-in | ver /ag-referencia-motion>
## Referências
- Design-library: <ID da variante — ex: 04b-split-text-image>
- Screenshots: <anexar ou descrever>
- URL inspiração: <opcional>
- Preset estético: <raiz-default | minimalist | brutalist | glass | outro>
## Constraints (stack rAIz)
- React 19 + TypeScript strict
- Tailwind v4 + shadcn/ui
- lucide-react para ícones (sem outras libs de icon)
- Mobile-first: `md:` e `lg:` para breakpoints
- Acessibilidade: aria-labels em elementos interativos sem texto, focus rings visíveis, labels em forms
- Placeholder content em PT-BR
- Tamanho: 50-200 linhas
- Sem business logic — apenas UI + handlers placeholder (`onClick?: () => void`)
## Entregável
<1 arquivo .tsx self-contained | múltiplos arquivos com estrutura X/Y/Z | spec markdown | prompt otimizado para v0>
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 First seen · 325 lines · 58 tokens per session scan A f8e35d58a02e
ag-referencia-prompt-guide is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 2,861 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
prompt-library-for-startups
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock…