Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/686f6c61/alfred-devnpx agentmods add skills/686f6c61/alfred-dev/style-directionWrote 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/686f6c61/alfred-dev/style-direction)<a href="https://agentmods.dev/skills/686f6c61/alfred-dev/style-direction"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/style-direction/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/686f6c61/alfred-dev/style-direction"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/style-direction.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 | $0.00040 | $0.02584 |
| Opus 5.5 | $0.00016 | $0.01034 |
| Sonnet 5.5 | $0.00008 | $0.00517 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
style-direction 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guía del servidor visual de Selina
Servidor local en navegador para mostrar sistemas de diseño y opciones visuales durante la fase de dirección de estilo. Funciona como un visual companion para enseñar el catálogo base de Selina, dejar que el usuario fije familia + tipografía + gama de color y cerrar después una ronda final de tres columnas.
Cuándo usar el servidor visual
Siempre que Selina genere opciones de estilo. El servidor es la herramienta principal de Selina: sirve tanto para enseñar la galería de 10 sistemas de diseño base como para el nuevo flujo guiado de selección y la ronda final de 3 propuestas comparables.
Arrancar sesión
visual/scripts/start-server.sh --project-dir /ruta/al/proyecto
Respuesta JSON esperada:
{
"type": "server-started",
"port": 7432,
"url": "http://localhost:7432",
"screen_dir": "/ruta/al/proyecto/.alfred-dev/visual/<pid-timestamp>/content",
"state_dir": "/ruta/al/proyecto/.alfred-dev/visual/<pid-timestamp>/state",
"state": "ready"
}
Guarda screen_dir (directorio donde escribir los HTML de opciones) y state_dir
(directorio donde leer eventos de clic y verificar estado del servidor).
El fichero state_dir/server-info contiene el mismo JSON emitido en el arranque.
Léelo para comprobar que el servidor sigue activo antes de cada operación.
Indica al usuario que abra la URL en el navegador.
El ciclo
- Comprueba que el servidor sigue activo leyendo
STATE_DIR/server-info. - Si aporta contexto, genera primero la galería del catálogo con
python3 visual/scripts/write-style-demo-gallery.py --visual-path "$STATE_DIR". - Flujo guiado recomendado:
python3 visual/scripts/write-style-selector.py --visual-path "$STATE_DIR"para elegir el sistema base.- lee la elección con
python3 visual/scripts/read-choice.py "$STATE_DIR". python3 visual/scripts/write-style-selector.py --visual-path "$STATE_DIR" --style-id "<style_id>"para que el usuario elija tipografía + paleta.- vuelve a leer la elección con
python3 visual/scripts/read-choice.py "$STATE_DIR". python3 visual/scripts/write-guided-style-options.py --visual-path "$STATE_DIR"para generar automáticamente la ronda final de 3 variantes a partir de esa selección.
- Flujo directo alternativo: si ya tienes las tres propuestas decididas, genera
screen_dir/style-options.htmlconpython3 visual/scripts/write-style-options.py --visual-path "$STATE_DIR". Si necesitas escribirlo a mano, usa la clase.style-grid. - El sidecar JSON final debe vivir en
screen_dir/style-options.jsonpara poder generar luego el artefacto final sin reinterpretar la pantalla. - Informa al usuario: recuerda la URL, resume qué se muestra, pide que elija una opción.
- En el siguiente turno: lee la elección final con
python3 visual/scripts/read-choice.py "$STATE_DIR"o, si lo prefieres, inspeccionaSTATE_DIR/eventsdirectamente. - Genera
docs/style-direction.mdconpython3 visual/scripts/write-style-direction.py --project-dir "$PWD" --visual-path "$STATE_DIR"o, si necesitas control manual, escribe el artefacto tú misma usando el sidecar JSON. - Escribe
waiting.htmlenscreen_dirpara limpiar el navegador hasta la próxima acción.
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 · 233 lines · 40 tokens per session scan A 02cd5901091c
style-direction is a skill published in the GitHub repository 686f6c61/alfred-dev (115 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 2,584 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 2026-08-30.
Other skills, from other repositories
frontend-design
A guide to building polished web interfaces, including their layout, colors, typography, responsive behavior, and interactive states.
prototype
Build a bounded disposable experiment to resolve a specific uncertainty. Triggers on "prototype", "原型".
a11y-review
A review of a website or application for accessibility, meaning whether people with disabilities can use it. It covers standards such as WCAG, keyboard controls, screen readers, focus, contrast, and color-based signals.
sxo
Search Experience Optimization (SXO), the bridge between SEO and UX/CRO. Audits the journey from the SERP click to the on-page goal: click-through factors (title, meta, rich results), then post-click signals that keep users and drive conversions: above-the-fold relevance and intent match, page speed / Core Web Vitals…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…