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/Carlos-Dominguez-faber/criterionpx agentmods add skills/carlos-dominguez-faber/criterio/design-auditWrote 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/carlos-dominguez-faber/criterio/design-audit)<a href="https://agentmods.dev/skills/carlos-dominguez-faber/criterio/design-audit"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/design-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/carlos-dominguez-faber/criterio/design-audit"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/design-audit.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 | $0.00138 | $0.02167 |
| Opus 5 | $0.00069 | $0.01084 |
| Sonnet 5 | $0.00028 | $0.00433 |
| Haiku 4.5 | $0.00014 | $0.00217 |
Grade A, and why
design-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 13d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-audit
Revisa la interfaz contra el contrato del proyecto, no contra un gusto ajeno.
En qué se diferencia de otros auditores
Los auditores de diseño que ya existen en el ecosistema juzgan tu código contra su criterio: sus reglas, su idea de lo que es una buena interfaz. Son útiles y vale la pena instalarlos.
Esta skill hace otra cosa: juzga tu código contra el contrato que tú escribiste. Si tu contrato dice warmth: 5 y tu botón es azul frío, eso es un fallo aquí aunque el azul esté impecablemente ejecutado. Y al revés: si tu contrato declara expression: 5 y una regla rota está anotada como deliberada, aquí no es un fallo.
La diferencia importa pedagógicamente: un auditor externo te enseña sus reglas; este te enseña a sostener las tuyas.
Procedimiento
Paso 1 — Localizar el contrato
Busca brand.json, voice.json, motion.json y COMPONENT_RULES.md en la carpeta brand/ del proyecto y, si no están ahí, en la raíz. Son los dos lugares donde el gate los busca; también acepta una ruta como argumento (node scripts/gate.mjs ./mi-app).
Si no hay contrato, para aquí. No improvises un criterio propio y no audites contra la nada. Di exactamente esto:
No encuentro un contrato de diseño en este proyecto. Sin contrato solo puedo darte mi opinión, que es justo lo que produce el problema que quieres arreglar. ¿Creamos uno? Son 8 preguntas y unos 5 minutos.
Y ofrece pasar a la skill design-contract. Si el usuario insiste en una revisión sin contrato, dale un diagnóstico corto (paleta detectada, familias detectadas, cuántos radios distintos, si hay transiciones sobre propiedades de layout) y márcalo claramente como observación, no auditoría.
Si el contrato está incompleto (existe brand.json pero falta motion.json, por ejemplo), audita lo que se pueda y reporta lo que falta como el primer hallazgo.
Paso 2 — Correr el gate
node scripts/gate.mjs
Exit 0 significa que los ocho checks pasan. Exit 1 significa que alguno falló —o que no encontró contrato— y la salida dice qué. Siete de los ocho checks leen el contrato; solo animated_props_safe lee el código del proyecto.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 115 lines · 138 tokens per session scan A cf3c267a1113
design-audit is a skill published in the GitHub repository Carlos-Dominguez-faber/criterio (55 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 2,167 once invoked, about $0.0007 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 2026-08-30.
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.