frontend-frontier

frontend-frontier is a skill for Claude Code, Codex from Kevin-Liu-01/Agent-Machines. It costs 53 tokens per session (1,992 once invoked), scanned A, original, MIT.

A guide for creating distinctive web interfaces with a deliberate visual style, motion, depth, and design system. It covers landing pages, dashboards, documentation sites, and other frontends.

In plain words
What is it for?
It is for planning and building branded pages, animation systems, parallax or 3D scenes, shader effects, and reusable design tokens while considering readability, performance, and reduced-motion settings.
Why use it?
It helps avoid generic layouts and disconnected visual effects by setting a clear design direction before implementation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for planning and building branded pages, animation systems, parallax or 3D scenes, shader effects, and reusable design tokens while considering readability, performance, and reduced-motion settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kevin-liu-01/agent-machines/frontend-frontier
Install

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.

Any agent
npx skills add Kevin-Liu-01/Agent-Machines --skill frontend-frontier
Clone the repo
git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for frontend-frontier

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-frontier/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-frontier)
Your own site
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-frontier"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-frontier/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.

agentmods 80×15 button for frontend-frontier

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/frontend-frontier"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/frontend-frontier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01992
Opus 5 $0.00026 $0.00996
Sonnet 5 $0.00011 $0.00398
Haiku 4.5 $0.00005 $0.00199

Measured 11d ago against content hash c04d6b2922e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

frontend-frontier 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 11d 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.

knowledge/skills/frontend-frontier/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Frontier

Use this skill when the job is not "make a page" but "make a page that actually has a point of view."

This skill is for:

  • unique landing pages and marketing sites
  • AI, devtools, and B2B SaaS frontends that need stronger taste
  • animation systems, scroll choreography, parallax, 3D, shaders, and hero scenes
  • design-system authoring, tokens, and consistency guardrails
  • turning loose inspiration into implementation-ready direction

Default stance

  • Do not drift into generic SaaS chrome.
  • Do not default to Inter, Roboto, shadcn, or arbitrary Tailwind soup unless the existing product already does.
  • Pick one art-direction thesis, one motion thesis, and one depth thesis before writing UI.
  • Build tokens before polishing components.
  • Treat motion as a system, not garnish.
  • CSS is substrate, not strategy. Use it for tokens, layout, fallbacks, and trivial states, not as the default animation architecture.
  • Default to a frontier stack: Tailwind v4 @theme, Motion, GSAP, Lenis, React Three Fiber, shaders/WebGL/WebGPU, and React transitions where appropriate.
  • Preserve performance, readability, and prefers-reduced-motion.
  • Sweat the micro-details. Great UI usually comes from many tiny correct choices compounding.

Workflow

  1. Lock the art direction.

Read references/aesthetic-systems.md.

Choose one primary mode:

  • editorial technical
  • cinematic 3D
  • architectural blueprint
  • neo-brutalist
  • experimental lab
  • premium AI SaaS

Write a 3-5 line direction covering:

  • visual thesis
  • type pairing
  • palette
  • surface treatment
  • motion grammar
  1. Choose the methodology lens.

Read references/design-methodology-atlas.md.

Pick:

  • one discovery methodology
  • one system methodology
  • one evaluation methodology
  1. Build the token system.

Read references/design-system-and-tokens.md.

Define:

  • color tokens
  • spacing scale
  • radii
  • shadows
  • border weights
  • type scale
  • z-index and blur tokens
  • motion tokens

Read the full file on GitHub · 232 lines

Changes

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.

  1. 11d ago First seen · 232 lines · 53 tokens per session scan A c04d6b2922e5

Subscribe to this mod's changes

frontend-frontier is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,992 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.

Related

Other skills, from other repositories

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

theme

Apply brand and visual direction in a Mantle application using its repo-owned theme and UI contracts.

aotter/mantle · 21 tokens

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

dmae97/omk · 61 tokens

saglitzdesign

Design, redesign, build, restyle, improve, critique, review, audit, simplify, polish, or animate a user interface — the front door into SaglitzDesign's eight design skills, for whichever one the work actually needs. Covers landing pages, marketing sites, dashboards, app screens, components, forms, onboarding, empty…

HalidSaglam/saglitzdesign-mcp · 204 tokens

figma-code-connect-design-system

Use when a FigJam board, product requirements document, reference image, Figma design file, published library, or codebase must become or update an evidence-traceable Figma design system, DTCG token hierarchy, platform-specific UI templates, production components, and verified Code Connect mappings. Covers create…

srinitude/skills · 105 tokens

mobile-first-website-design

Use when designing landing pages and marketing websites.

srinitude/skills · 15 tokens