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 parisgroup-ai/imersao-ia-setup --skill pwa-auditgit clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setupWrote 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/parisgroup-ai/imersao-ia-setup/pwa-audit)<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/pwa-audit"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/pwa-audit/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/parisgroup-ai/imersao-ia-setup/pwa-audit"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/pwa-audit.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 | $0.00039 | $0.01654 |
| Opus 5 | $0.00019 | $0.00827 |
| Sonnet 5 | $0.00008 | $0.00331 |
| Haiku 4.5 | $0.00004 | $0.00165 |
Grade A, and why
pwa-audit 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 12d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PWA Audit
Scanner que detecta violacoes de usabilidade mobile-first em componentes React/TSX.
Diferenca do mobile-pwa-usability
| Skill | Proposito |
|---|---|
mobile-pwa-usability |
Guia — checklist para aplicar ao construir componentes |
pwa-audit |
Scanner — busca violacoes em codigo existente |
Quando Usar
- Apos criar/modificar multiplos componentes interativos
- Auditoria periodica de compliance PWA
- Sprint de revisao mobile-first (como o sprint PWA Review)
- Antes de release que afeta componentes de UI
Criterios de Auditoria
| Criterio | Regra | Padrao Correto | Violacao |
|---|---|---|---|
| Touch targets | min 44x44px | min-h-[var(--touch-target-min)] |
h-6, h-8, p-1, p-1.5 em botoes |
| Font size inputs | min 16px | text-base |
text-sm, text-xs em <input>, <textarea>, <select> |
| Touch manipulation | Eliminar tap delay | touch-manipulation |
Ausencia em elementos clicaveis |
| Search inputs | Semantica mobile | type="search" + inputMode="search" |
type="text" em campos de busca |
| Safe areas | Suporte notch | env(safe-area-inset-*) |
Elementos fixos sem safe area |
Procedimento de Scan
Fase 1: Definir Escopo
Determinar quais arquivos auditar:
# Escopo completo (todos os componentes interativos)
find src -name "*.tsx" | grep -v __tests__ | grep -v '.test.' | grep -v '.stories.'
# Por layer
find src/primitives -name "*.tsx" | grep -v __tests__
find src/layouts -name "*.tsx" | grep -v __tests__
find src/interactions -name "*.tsx" | grep -v __tests__
find src/composites -name "*.tsx" | grep -v __tests__
Fase 2: Scan Automatizado
Buscar padroes de violacao com grep/ripgrep:
Touch Targets Insuficientes
# Botoes com padding pequeno (provavelmente < 44px)
rg '(className.*button|<button|<Button)' --type tsx -l | \
xargs rg 'p-1[^0-9]|p-1\.5|h-6 |h-7 |h-8 |w-6 |w-7 |w-8 ' --type tsx -n
# Botoes SEM touch target minimo
rg '<button' --type tsx -l | \
xargs rg -L 'touch-target-min|min-h-\[44|min-h-\[2\.75' --type tsx
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.
- 12d ago First seen · 191 lines · 39 tokens per session scan A 865326e60984
pwa-audit is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,654 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
create-mobile-app
Use when the user wants to start a new Power Apps mobile app (Expo / React Native / TypeScript, targeting iOS and Android) from scratch.
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…
create-website
Guided journey from a blank page to a live, high-converting website, built message-first, then design, then conversion. Orchestrates ten skills phase by phase - one-page-marketing, storybrand-messaging, made-to-stick, top-design, web-typography, refactoring-ui, ux-heuristics, cro-methodology, scorecard-marketing…
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…
high-perf-browser
Optimize web performance through network protocols, resource loading, and browser rendering internals. Use when the user mentions "my site is slow", "Core Web Vitals", "HTTP/2 or HTTP/3", "resource hints", "network latency", "render blocking", "TCP/TLS optimization", "service worker", "Cache-Control or caching…