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 jnPiyush/AgentX --skill design-system-reasoninggit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/design-system-reasoning)<a href="https://agentmods.dev/skills/jnpiyush/agentx/design-system-reasoning"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/design-system-reasoning/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/jnpiyush/agentx/design-system-reasoning"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/design-system-reasoning.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 | $0.00066 | $0.02627 |
| Opus 5.5 | $0.00026 | $0.01051 |
| Sonnet 5.5 | $0.00013 | $0.00525 |
| Haiku 4.5 | $0.00007 | $0.00263 |
Grade A, and why
design-system-reasoning 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Reasoning
WHEN: Choosing UI direction, selecting a visual language, defining design tokens, filtering anti-patterns, or turning a vague product brief into a design-system-ready implementation plan.
When to Use This Skill
- Turning a product description into a usable UI direction
- Deciding which page archetype fits a product or feature
- Choosing a restrained visual language before coding begins
- Defining token guidance for color, typography, spacing, and motion
- Documenting anti-patterns for regulated, trust-sensitive, or data-heavy products
- Translating the same design intent across Tailwind, React, Vue, SwiftUI, Flutter, or plain HTML/CSS
- Reviewing whether a proposed UI direction matches audience expectations
Quick Reference
| Need | Use |
|---|---|
| Product is vague | Fill the design brief template first |
| Screen structure is unclear | Choose a page archetype before styling |
| Domain risk is high | Define anti-patterns and trust cues first |
| UI feels trendy but wrong | Re-check posture, density, and trust fit |
| Multi-stack delivery | Preserve intent, then translate per stack |
Decision Tree
Need UI direction, not just polished screens?
|
+-- Product is vague or early-stage?
| -> Create a design brief first
|
+-- Marketing / landing page?
| -> Pick a page archetype before colors or typography
|
+-- Dashboard / admin / analytics?
| -> Start from information density, hierarchy, and task frequency
|
+-- Regulated / trust-sensitive domain?
| -> Define anti-patterns and confidence cues before visual style
|
+-- Multi-platform delivery?
| -> Lock design intent, then translate to each stack separately
|
- Existing UI feels off but not obviously broken?
-> Run the critique rubric and identify mismatch: tone, hierarchy, density, motion, or trust
Core Rules
- Choose the product posture first - classify the experience as trust-led, workflow-led, exploration-led, emotion-led, or utility-led before picking a style.
- Select page archetypes before aesthetics - decide whether the screen is proof-led, conversion-led, workflow-led, editorial, or operational before picking colors or effects.
- Write anti-patterns explicitly - every design brief MUST include what the UI must avoid for that domain, not only what it should include.
- Tokens before components - define color, type, spacing, radius, shadow, and motion rules before expanding into component examples.
- Constrain visual intensity - decorative effects must support the product goal; if the interface competes with the task, reduce it.
- Translate intent, not literal classes - when switching stacks, preserve hierarchy, density, and interaction semantics rather than copying markup patterns.
What ships with it
7 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 Changed 07a38597292d
- 1mo ago First seen · 227 lines · 66 tokens per session scan A c50ea0078f5a
design-system-reasoning is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,627 once invoked, about $0.0003 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 2026-09-03.
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.