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 alt-textgit 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/alt-text)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/alt-text"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/alt-text/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/alt-text"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/alt-text.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 | $0.00077 | $0.00812 |
| Opus 5 | $0.00039 | $0.00406 |
| Sonnet 5 | $0.00015 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
alt-text 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 7d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Texto Alternativo
Você escreve o que a pessoa que não vê a imagem precisa receber.
Princípio central
Alt text não descreve a imagem. Transmite a informação que a imagem carrega.
Duas peças visualmente idênticas com propósitos diferentes recebem alt texts diferentes.
Regras
Comece pela informação, não pelo meio. ❌ "Imagem de um card com fundo verde mostrando..." ✅ "Fechamento do mês caiu de 11 dias para 20 minutos após a integração."
Leitor de tela já anuncia que é imagem. Repetir gasta o tempo de quem escuta.
Transcreva todo texto da peça. Se há texto na imagem, ele precisa estar no alt. Texto em pixel é invisível para leitor de tela.
Tamanho: 1-2 frases para peça simples; até 4 para card de dado ou infográfico. Sem limite rígido, mas alt longo demais cansa — se precisar de mais, o conteúdo deveria estar na legenda.
Sem "imagem de", "foto de", "gráfico mostrando". Vá direto.
Descreva pessoas com neutralidade. Só mencione característica física se for relevante para a informação. Não infira gênero, idade, etnia ou condição a partir da aparência — se a informação não estiver confirmada, descreva o que a pessoa faz, não o que você supõe que ela é.
Dado precisa do número. "Gráfico de crescimento" é inútil. "Atendimentos subiram de 1.200 para 3.400 entre janeiro e junho de 2026" serve.
Por tipo
| Tipo | O que o alt precisa ter |
|---|---|
| Quote card | a frase completa + quem disse |
| Card de dado | o número, a unidade, o período, a fonte |
| Carrossel | um alt por slide, cada um autônomo |
| Screenshot de produto | o que a tela mostra e o que isso significa |
| Foto de pessoas | a ação e o contexto, sem inferir identidade |
| Peça institucional | a informação de serviço completa |
Carrossel
Um alt por slide. Cada um precisa fazer sentido sozinho — a pessoa pode entrar em qualquer slide. É o formato que mais falha em acessibilidade, porque o time escreve um alt só e aplica em todos.
Onde entra
| Plataforma | Onde |
|---|---|
| Configurações avançadas → texto alternativo | |
| botão Alt ao anexar | |
| editar texto alternativo | |
| X | "Adicionar descrição" |
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.
- 7d ago First seen · 98 lines · 77 tokens per session scan A bf9300be18ee
alt-text is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 812 once invoked, about $0.0004 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 $ralph 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.