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-redesign-workflowgit 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-redesign-workflow)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-referencia-redesign-workflow"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-redesign-workflow/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-redesign-workflow"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-referencia-redesign-workflow.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 | $0.00052 | $0.02475 |
| Opus 5.5 | $0.00021 | $0.00990 |
| Sonnet 5.5 | $0.00010 | $0.00495 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
ag-referencia-redesign-workflow 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redesign Workflow — Screenshot → Variante + Preset + Prompt
Diferencial real vs GlowUp UI: inputar screenshot/URL e receber mapeamento preciso para nossa biblioteca interna (86 variantes) + prompt pronto para regerar. Complementa /ag-referencia-design-presentation (taxonomia) e /ag-referencia-prompt-guide (estrutura de prompt).
Quando usar
- Cliente/stakeholder manda screenshot pedindo "quero isso no nosso app"
- Cliente manda URL concorrente pedindo redesign competitivo
- App rAIz legado precisa refresh — captura tela atual, recomenda variante moderna
- Dev não sabe qual variante escolher — dá input visual, recebe sugestão
Quando NÃO usar
- Componente isolado (botão, input) — usar /presentation direto por navegação
- Feature com business logic complexa — UI só cobre 20% do trabalho, o resto é domínio
- Projeto sem tokens rAIz — workflow pressupõe output adaptado ao design-system da empresa
Entradas aceitas
| Tipo | Como fornecer | Ferramenta de captura |
|---|---|---|
| URL pública | "redesign https://example.com" | Chrome DevTools MCP navigate_page + take_screenshot |
| URL localhost | "redesign http://localhost:3011/x" | idem |
| Screenshot upload | colar PNG/JPG na conversa | Claude multimodal direto (sem captura) |
| Path local | "redesign ~/screenshots/app.png" | Read tool direto |
| Figma URL | "redesign figma.com/file/..." | figma-implement-design skill primeiro |
Pipeline de 5 passos
1. Captura
Se URL: Chrome DevTools MCP
mcp__plugin_chrome-devtools-mcp_chrome-devtools__navigate_page({ url: "..." })
mcp__plugin_chrome-devtools-mcp_chrome-devtools__take_screenshot({ fullPage: true })
Se screenshot/upload: já está disponível, pular captura.
Salvar em ~/Claude/docs/diagnosticos/redesign-<timestamp>/input.png para auditoria.
2. Análise visual (Claude multimodal)
Enviar screenshot com prompt estruturado de classificação:
Analise este screenshot e classifique:
1. Categoria dominante (escolha 1-2 de):
- 01 Auth Forms (login, signup)
- 02 Pricing
- 03 Features/Bento
- 04 Hero Sections
- 05 CTA Banners
- 06 Stats / Social Proof
- 07 Nav Bars
- 08 Testimonials
- 09 Footer
- 10 FAQ
- 11 Onboarding (checklist, tour)
- 12 Blog / Content
- 13 Contact
- 14 States (404, loading, empty)
2. Estilo estético percebido (escolha 1):
- raiz-default: laranja + teal, rounded-xl, shadows sutis, Inter
- minimalist: sem sombras, mono slate, tipografia fina
- brutalist: rounded-none, borders pretas, shadows offset duros
- glass: backdrop-blur, semi-transparent, glow
- dark-mono: fundo quase-preto, zinc scale, branco puro como acento
- soft-saas: pastéis lavanda/pêssego, rounded-3xl, shadows difusas
- neobrutalism: rounded-md, shadows offset coloridas, pastéis saturados
3. Estrutura geométrica em 1 frase (ex: "split 50/50 form+hero", "3-tier cards", "bento 4-tile").
4. Tom/voz percebido (ex: "corporate B2B", "startup playful", "editorial", "gaming").
Output JSON:
{
"category": "04 Hero Sections",
"subtype_hint": "04b-split-text-image OR 04c-animated-gradient",
"style": "raiz-default",
"structure": "split 50/50 texto+screenshot",
"voice": "SaaS corporate B2B",
"confidence": "high|medium|low",
"notes": "..."
}
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 · 271 lines · 52 tokens per session scan A 940fe5264219
ag-referencia-redesign-workflow is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,475 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.