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.
git clone --depth 1 https://github.com/Mazalucas/El-DT-Lightweight-ArmyWrote 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/rules/mazalucas/el-dt-lightweight-army/20-frontend-ui)<a href="https://agentmods.dev/rules/mazalucas/el-dt-lightweight-army/20-frontend-ui"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/20-frontend-ui/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/rules/mazalucas/el-dt-lightweight-army/20-frontend-ui"><img src="https://agentmods.dev/badge/rules/mazalucas/el-dt-lightweight-army/20-frontend-ui.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 | $0.00000 | $0.00410 |
| Opus 5.5 | $0.00000 | $0.00164 |
| Sonnet 5.5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
20-frontend-ui 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 2mo 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.
What it actually says
Frontend y UI
Stack default del DT: ver regla 08-stack-web-default y vitals/data/engineering/web-stack.yaml.
Stack default (proyecto web nuevo)
- Bundler: Vite
- UI: React (componentes funcionales)
- Backend client: Firebase JS SDK modular (v9+)
- Alternativas permitidas: React solo, Vite solo — según
web-stack.yaml
Si el repo ya usa otro framework, respetarlo (soft default).
Componentes
- Usar componentes funcionales
- Extraer hooks para lógica reutilizable
- Colocar estilos cerca de componentes
- Preferir composición sobre herencia
Estado
- Estado local para UI; estado global solo cuando cruza muchos componentes
- Evitar prop drilling excesivo; considerar context o state management
Accesibilidad
- Atributos ARIA cuando sea necesario
- Labels en formularios
- Contraste de colores
- Navegación por teclado
Performance
- Lazy load de rutas/componentes pesados
- Memoización cuando el costo de re-render es alto
- Imágenes optimizadas
Reutilización (reuse-first)
Regla transversal: 15-engineering-reuse · skill frontend · DOC-REF-006.
- No duplicar componentes — buscar en
components/,ui/, hooks existentes; variant props antes de archivo nuevo - Tokens semánticos del design system o Atelier — no hex sueltos si hay handoff
- Handoff Atelier: implementar
component-specstal cual (skillfrontend/references/atelier-handoff.md) - Composición sobre copiar markup entre páginas
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.
- 2mo ago First seen · 53 lines · 0 tokens per session scan A 423a0f350228
20-frontend-ui is a cursor rule published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 tokens. 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.
20-frontend-ui compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 20-frontend-uiMazalucas/El-DT-Lightweight-Army | Cursor rule | 4 | yesterday | MIT | A | 0 | Cursor |
| nextjs-react-tailwind-cursorrules-prompt-filePatrickJS/awesome-cursorrules | Cursor rule | 41k | 5mo ago | CC0-1.0 | A | 891 | Cursor |
| chakra-ui-best-practicesholtwood/awesome-cursorrules-zh | Cursor rule | 241 | 18d ago | MIT | A | 0 | Cursor |
| react-components-creation-cursorrules-prompt-filePatrickJS/awesome-cursorrules | Cursor rule | 41k | 5mo ago | CC0-1.0 | A | 355 | Cursor |
| react-styled-components-cursorrules-prompt-filePatrickJS/awesome-cursorrules | Cursor rule | 41k | 5mo ago | CC0-1.0 | A | 243 | Cursor |
| componentskensaurus/cursor-kenji | Cursor rule | 9 | 1mo ago | MIT | A | 0 | Cursor |
| stylingGoranErhartic/cursor-development-rules | Cursor rule | 20 | 8mo ago | MIT | A | 17 | Cursor |