copilot-kit frontend.instructions.md

A set of frontend and user-interface coding standards for building web interfaces, covering layout, colors, spacing, accessibility, touch targets, performance, and Tailwind CSS.

In plain words
What is it for?
Use it when creating or reviewing web interfaces, especially mobile-first layouts, responsive components, images, animations, or Tailwind-based projects.
Why use it?
It gives UI work consistent rules for responsive design, accessible controls, visual hierarchy, and efficient browser behavior.

Instructions file for GitHub Copilot

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.

agentmods
npx agentmods add instructions/ivanshtokov/copilot-kit/frontend
Clone the repo
git clone --depth 1 https://github.com/ivanshtokov/copilot-kit

Made for: GitHub Copilot.

Per session 331 This file is loaded in full into every session.
When invoked 331 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00331 $0.00331
Opus 5 $0.00166 $0.00166
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured yesterday against content hash d24bbd075d50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-kit frontend.instructions.md 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 yesterday.

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.

.github/instructions/frontend.instructions.md · 47 lines

What it actually says

Frontend/UI Standards

🎨 Before Any UI Work

READ: .github/skills/frontend-design/SKILL.md

⚠️ ANTI-PATTERNS (NEVER DO)

❌ Don't ✅ Do
Bento grids everywhere Ask if grid is needed
Mesh/Aurora gradients Consider solid colors first
Dark + neon as default Ask for color preference
Same layout every time Vary based on content
Skip asking preferences Always ask when unclear

📐 Core Principles

  1. Mobile-first: Start with mobile, scale up
  2. 8-point grid: Use multiples of 8 for spacing
  3. 60-30-10 color rule: Primary 60%, Secondary 30%, Accent 10%
  4. Accessibility: WCAG 2.1 AA minimum

🎯 Touch Targets

  • Minimum 44px × 44px for mobile
  • 8px+ spacing between targets
  • Primary CTAs in thumb zone

⚡ Performance

  • Lazy load images below fold
  • Use loading="lazy" on images
  • Prefer CSS animations over JS
  • Animate only transform and opacity

🔧 Tailwind (if used)

  • Use design system scale, not arbitrary values
  • Extract repeated patterns to components
  • Follow v4 CSS-first configuration
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. yesterday First seen · 47 lines · 331 tokens per session scan A d24bbd075d50

Subscribe to this mod's changes

copilot-kit frontend.instructions.md is an instructions file published in the GitHub repository ivanshtokov/copilot-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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 2026-08-31.