A set of rules for creating, changing, and troubleshooting user-interface code, including page layouts, styles, and frontend structure. It also covers accessibility, which makes interfaces usable by people with disabilities.

Use it when building or modifying UI components, writing CSS, organizing frontend code, or investigating visual bugs. It guides the use of shared design values and visible keyboard focus.

It helps avoid inconsistent styling, inaccessible controls, and visual problems caused by arbitrary design choices.

How rafaelghif/antigravity-agents configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to rafaelghif/antigravity-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/rafaelghif/antigravity-agents/main/.agents/skills/design/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/rafaelghif/antigravity-agents

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/design/github.svg)](https://agentmods.dev/skills/rafaelghif/antigravity-agents/design)

Your own site

<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/design"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/design"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,159 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01159
Opus 5.5	$0.00015	$0.00464
Sonnet 5.5	$0.00007	$0.00232
Haiku 4.5	$0.00004	$0.00116

Measured 1mo ago against content hash 0c335029000f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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.

.agents/skills/design/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Design, Accessibility & Web Performance Protocol

Role: Staff Frontend Architect & Design Systems Lead.

Overview & Trigger Conditions

Activate this skill when creating or modifying UI components, styling layouts (CSS/Tailwind), implementing design token systems, auditing accessibility (WCAG 2.2 AA), or optimizing frontend runtime performance (Core Web Vitals).

Trigger Scenarios & Keywords:

UI/UX component development, styling refactors, responsive layouts, web performance audits.
Keywords: ui, ux, component, styling, css, tailwind, accessibility, a11y, wcag, webperf, core web vitals, lcp, inp, cls.

Core Standards & Invariants

DTCG 3-Tier Design Tokens (SSOT):
- Tier 1 (Primitive): Raw palette scales and fixed metrics (colors.slate.900, spacing.4).
- Tier 2 (Semantic): Intent-driven tokens (color.bg.surface, color.text.muted, action.primary.hover).
- Tier 3 (Component): Scoped component tokens (button.primary.bg, input.border.focus).
- Strictly ban hardcoded hex codes (#1e293b) and arbitrary pixel values inside components. Map styles to design tokens or Tailwind theme utilities.
WCAG 2.2 Level AA Accessibility (a11y):
- Color Contrast: Minimum contrast ratio of $\ge 4.5:1$ for normal text, and $\ge 3:1$ for large text and interactive boundaries.
- Focus Visible: NEVER remove outlines (outline-none) without an explicit replacement (focus-visible:ring-2 focus-visible:ring-offset-2). Enforced by ui_hygiene_guard.py.
- Touch Target Sizing: Interactive elements must provide a minimum $44 \times 44\text{ px}$ target area with $\ge 8\text{px}$ spacing between adjacent targets.
- Semantic Markup: All <img> tags must include meaningful alt attributes (or alt="" if decorative); <button> elements require explicit type="button" or type="submit".
Core Web Vitals & Runtime Performance:
- LCP ($\le 2.5\text{s}$): Preload hero images (fetchpriority="high"). Self-host web fonts with font-display: swap. Eliminate render-blocking waterfalls.
- INP ($\le 200\text{ms}$): Chunk long JavaScript tasks $> 50\text{ms}$ using scheduler.yield(). Throttle/debounce scroll and resize listeners.
- CLS ($\le 0.1$): Always specify explicit width/height or CSS aspect-ratio on images, videos, and dynamic iframes.

Read the full file on GitHub · 73 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.

1mo ago Changed 0c335029000f
2mo ago Changed b479bda6abaa
2mo ago Changed · +33 lines 74bb3b7f724a
2mo ago Changed · -11 lines · +8 tokens per session 95824d8f1ac5
2mo ago First seen · 51 lines · 29 tokens per session scan A c60cf2abc031

Subscribe to this mod's changes

design is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,159 once invoked, about $0.0001 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 2026-08-31.

CI and CD CSS and styling Design and UX Frontend agentic-workflow ai-agents antigravity mcp multi-agent-systems

design next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
designrafaelghif/antigravity-agents	Skill	5	1mo ago	MIT	A	37	Claude Code, Codex
ui-first-builderwasintoh/toh-framework	Skill	96	2mo ago	MIT	A	75	Claude Code, Codex
frontend-design-systemmnzralee/claude-multi-agent-architecture	Skill	8	1mo ago	MIT	A	188	Claude Code
frontend-ui-engineeringaddyosmani/agent-skills	Skill	114k	5d ago	MIT	A	58	Claude Code
anti-slop-designsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	34	Claude Code
antigravity-design-expertsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	39	Claude Code
mcp-host-styling-integrationa5c-ai/babysitter	Skill	1.9k	5d ago	MIT	A	44	Claude Code

antigravity-agents: Skill for Claude Code