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 gethouston/houston --skill frontend-designgit clone --depth 1 https://github.com/gethouston/houstonWrote 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/gethouston/houston/frontend-design)<a href="https://agentmods.dev/skills/gethouston/houston/frontend-design"><img src="https://agentmods.dev/badge/skills/gethouston/houston/frontend-design/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/gethouston/houston/frontend-design"><img src="https://agentmods.dev/badge/skills/gethouston/houston/frontend-design.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 | $0.00068 | $0.01478 |
| Opus 5 | $0.00034 | $0.00739 |
| Sonnet 5 | $0.00014 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
frontend-design 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 9d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/frontend-design
Design like the lead at a studio that gives every product an identity no one else could mistake. Deliberate, opinionated choices — but always inside Houston's system. Distinctiveness here is earned through restraint and precision, not novelty for its own sake.
Precondition — load the system FIRST
Before any pixel:
- Read
/DESIGN.md(repo root) FIRST — the agent-facing spec you hold in context (identity, hard rules, token quick-reference, motion, banned defaults, polish checklist, component inventory). Then read the existing components of the surface you touch. - Token VALUES are authoritative in
packages/design-tokens/tokens/*.json(semantic--ht-*alias layer, light + dark). Never a hardcoded hex/spacing literal — a visual change is a token edit. - Search before building:
@houston-ai/*showcase, existingapp/srccomponents, shadcn/ui registry. Reuse beats invention (houston/CLAUDE.md→ Search before building).
The design system wins on any conflict. This skill adds process; it never overrides a documented token, rule, or pattern.
Two-pass discipline
Pass 1 — commit direction BEFORE code
Write a compact plan, entirely within Houston's tokens. Keep it in your thinking / a scratch note; show the user only once you're confident:
- Layout concept — one-sentence prose + an ASCII wireframe. Place it on the real surface ladder (
bg-backgroundcanvas,bg-cardfloats,bg-inputfields — design-system.md → The surface ladder; there is nolayer-*token). - Hierarchy — name the ONE focal point. One obvious action per screen (Show, don't configure).
- The signature element — the single thing this surface is remembered by, drawn from Houston's world (the composer's multi-shadow lift, the card-running-glow, the aurora chrome). Spend boldness here.
- Motion moments — where (if anywhere) animation serves: a load sequence, a reveal, a hover micro-interaction. Use only the vocabulary in design-system.md → Animation (durations, springs,
card-running-glow, framer springs). Less is usually more. - Copy — the real strings, in Houston's voice (see Copy rules below).
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.
- 9d ago First seen · 78 lines · 68 tokens per session scan A 67cbc1d6d1b8
frontend-design is a skill published in the GitHub repository gethouston/houston (112 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,478 once invoked, about $0.0003 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…