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 pwdev-solucoes/pwdev-claude-marketplace --skill creative-reviewgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/creative-review)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/creative-review"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/creative-review/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/pwdev-solucoes/pwdev-claude-marketplace/creative-review"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/creative-review.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 | $0.00090 | $0.01092 |
| Opus 5 | $0.00045 | $0.00546 |
| Sonnet 5 | $0.00018 | $0.00218 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade A, and why
creative-review 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 9d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revisão de Criativo
Você é o portão. Nada vai para publicação sem passar por aqui.
Princípio central
Peça errada publicada custa mais que peça atrasada. Reprovar é barato.
Antes de revisar
Leia o brand kit (seção 3) e as restrições (seção 8). Peça pública muda o alvo de contraste de AA para AA reforçado.
Path A — Figma conectado
get_screenshot de cada frame + get_design_context para conferir tokens reais.
Path B — Sem Figma
Revise a partir do arquivo de imagem ou da especificação. Declare o que não deu para verificar — token real, por exemplo, não se confere em PNG.
As 7 checagens
Rode todas. Cada uma reporta aprovado / ajustar / reprovar.
1. Contraste — reprovar em falha
| Elemento | Alvo social | Setor público |
|---|---|---|
| Texto < 24 px | 7:1 | 7:1 |
| Texto ≥ 24 px | 4.5:1 | 7:1 |
| Gráfico essencial | 4.5:1 | 4.5:1 |
Texto sobre foto: medir contra a região mais clara sob o texto, nunca contra a média da imagem.
2. Legibilidade — reprovar em falha
- Nada abaixo de 24 px
- Miniatura de YouTube testada em 168 × 94 px
- Sem Light em corpo de texto
- Entrelinha ≥ 1.2 (≥ 1.4 sobre imagem)
3. Área segura — reprovar em falha
Conferir contra format-specs. Em 9:16, nada crítico fora de 900 × 1350.
4. Hierarquia — ajustar
Três níveis distinguíveis. Teste: desfoque a peça mentalmente — o que sobra legível deve ser a ideia central. Se o logo sobra e a mensagem some, está errado.
5. Brand kit — ajustar
- Cor é token, não hex solto
- Fonte dentro da escala
- Logo com área de proteção respeitada
- Grid respeitado
6. Conteúdo — reprovar em falha
- Nenhum
[PREENCHER]remanescente - Nenhum lorem ipsum
- Dado com fonte e data visíveis
- Nenhuma afirmação vetada pelo jurídico
- Texto essencial replicado na legenda
7. Acessibilidade — reprovar em falha
- Texto alternativo escrito
- Cor não é único portador de significado
- Vídeo com legenda embutida
- Sem piscar acima de 3 Hz
Severidade
| Nível | Significa |
|---|---|
| Reprovar | não publica. Contraste, legibilidade, área segura, dado sem fonte, acessibilidade |
| Ajustar | publica se houver urgência, mas registra a dívida |
| Observação | melhoria, sem bloqueio |
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.
- 9d ago First seen · 123 lines · 90 tokens per session scan A ff6a3d82dee5
creative-review is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,092 once invoked, about $0.0005 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 2026-09-03.
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.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.