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-contractWrote 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-contract)<a href="https://agentmods.dev/skills/carlos-dominguez-faber/criterio/design-contract"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/design-contract/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-contract"><img src="https://agentmods.dev/badge/skills/carlos-dominguez-faber/criterio/design-contract.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 | $0.00143 | $0.03161 |
| Opus 5.5 | $0.00057 | $0.01264 |
| Sonnet 5.5 | $0.00029 | $0.00632 |
| Haiku 4.5 | $0.00014 | $0.00316 |
Grade A, and why
design-contract 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 1mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-contract
Genera el contrato de diseño de un proyecto: cuatro archivos que el agente lee antes de escribir cualquier componente.
Por qué existe
Un modelo de lenguaje sin contrato no elige: promedia. Devuelve la mediana estadística de todo lo que vio en entrenamiento, y esa mediana tiene tells reconocibles (Inter, índigo, radio de 16px en todo, hero centrado, tres tarjetas). Eso no es falta de capacidad: es falta de criterio, y el criterio se escribe, no se pide.
Esta skill convierte adjetivos ("moderno", "limpio", "premium") en datos verificables: seis ejes numéricos, hex con nombre, reglas con número. Lo que un humano puede discutir y una máquina puede revisar.
Qué produce
| Archivo | Quién lo lee | Qué contiene |
|---|---|---|
brand.json |
el agente y gate.mjs |
identidad, arquetipo, los 6 ejes, tokens, reglas de componente, anti-slop, validación |
voice.json |
el agente cuando escribe copy | idioma y dialecto, ejes de tono, palabras prohibidas y seguras, estilo de CTA |
motion.json |
el agente cuando anima | personalidad, duraciones, curvas, props seguras e inseguras, reglas |
COMPONENT_RULES.md |
el agente y el humano | las reglas anteriores en prosa, por componente |
Además, node scripts/tokens.mjs compila brand.json a brand.css con tokens en tres niveles (primitivos, semánticos, de componente). El CSS es generado: no se edita a mano.
Procedimiento
Paso 0 — Reconocer el terreno
- Busca en la raíz del proyecto:
brand.json,voice.json,motion.json,COMPONENT_RULES.md. - Si ya existen, no los sobrescribas. Di qué encontraste y ofrece tres caminos: revisar y ajustar campos concretos, extender con lo que falte, o empezar de cero con respaldo previo (
brand.json.bak). - Si el proyecto ya tiene UI escrita, léela por encima (paleta usada, fuentes cargadas, radios) para poder proponer valores en vez de preguntar todo desde cero.
- Detecta el stack (Tailwind, CSS plano, CSS modules, styled-components). Solo afecta la salida de
brand.cssy las notas deCOMPONENT_RULES.md; las decisiones de las secciones de identidad, postura, color, tipografía y forma son agnósticas al stack.
What ships with it
3 files 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.
- 1mo ago First seen · 163 lines · 143 tokens per session scan A 9b7bc6fe196c
design-contract is a skill published in the GitHub repository Carlos-Dominguez-faber/criterio (58 stars, last pushed 3mo ago), licensed MIT. It adds 143 tokens to every session and 3,161 once invoked, about $0.0006 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
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.