lovable-boilerplate design.instructions.md

lovable-boilerplate design.instructions.md is an instructions file for GitHub Copilot from chihebnabil/lovable-boilerplate. It costs 4,058 tokens per session, scanned A, original, MIT.

A set of interface design instructions for the Lovable Boilerplate project, covering visual style, accessibility, responsive layouts, and animations. Accessibility means making interfaces usable by people with disabilities.

In plain words
What is it for?
It guides the creation of mobile-friendly interfaces with industry-appropriate colours, clear hierarchy, readable contrast, whitespace, and purposeful animations. It also calls for WCAG 2.1 AA accessibility standards.
Why use it?
It sets consistent design requirements and helps prevent low-contrast, generic, hard-to-use, or non-responsive interfaces.

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/chihebnabil/lovable-boilerplate/design
Clone the repo
git clone --depth 1 https://github.com/chihebnabil/lovable-boilerplate

Made for: GitHub Copilot.

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 lovable-boilerplate design.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chihebnabil/lovable-boilerplate/design.svg)](https://agentmods.dev/instructions/chihebnabil/lovable-boilerplate/design)
Your own site
<a href="https://agentmods.dev/instructions/chihebnabil/lovable-boilerplate/design"><img src="https://agentmods.dev/badge/instructions/chihebnabil/lovable-boilerplate/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,058 This file is loaded in full into every session.
When invoked 4,058 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 $0.04058 $0.04058
Opus 5 $0.02029 $0.02029
Sonnet 5 $0.00812 $0.00812
Haiku 4.5 $0.00406 $0.00406

Measured 5d ago against content hash a20358d7147a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lovable-boilerplate design.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 5d 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.

.github/instructions/design.instructions.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design System Guidelines

CRITICAL DESIGN RULES

NEVER CREATE:

  • Poor accessibility - must maintain 4.5:1 contrast ratio minimum
  • Generic designs - always adapt to target industry/audience
  • Template-like layouts - create unique, custom-crafted interfaces
  • Static interfaces - include sophisticated micro-interactions
  • Default grays (slate-400, gray-500) - use rich, intentional color palettes

ALWAYS CREATE:

  • Industry-appropriate design - adapt colors/typography to target audience
  • Premium visual hierarchy - sophisticated use of scale, contrast, spacing
  • Accessible interfaces - WCAG 2.1 AA compliant (4.5:1 text contrast)
  • Mobile-first responsive - progressive enhancement approach
  • Purposeful animations - enhance usability, not just decoration

Core Design Philosophy

Every interface must feel like it was crafted by a top-tier design agency.

  • Emotional Impact First: Ask "Does this make users stop and say 'wow'?"
  • Sophisticated Hierarchy: Use contrast, scale, and spacing strategically
  • Purposeful Motion: Every animation should enhance usability
  • Breathing Room: Generous whitespace creates luxury feel
  • Cohesive Visual Story: Design choices should work together harmoniously
  • Unique Visual Identity: Design should feel custom-crafted, never template-like
  • Industry-Appropriate Design: Visual language should match the target audience and use case
  • Color Psychology: Use colors intentionally to evoke the right emotions and associations

Visual Quality Standards

NEVER CREATE:

  • Generic card grids with default shadows
  • Plain white backgrounds with black text
  • Basic hover states (simple color changes)
  • Template-like layouts
  • Uniform spacing everywhere
  • Overuse of default Tailwind grays without intention
  • Static, lifeless interfaces
  • Color choices without consideration for brand or industry context

ALWAYS CREATE:

  • Dynamic, engaging compositions with visual flow
  • Rich, intentional color palettes that serve the design purpose
  • Sophisticated micro-interactions
  • Asymmetrical layouts that guide the eye
  • Varied spacing that creates rhythm
  • High contrast, accessible text combinations
  • Interactive, responsive designs with personality
  • Color schemes that enhance the user experience and brand message

Read the full file on GitHub · 384 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. 5d ago First seen · 384 lines · 4,058 tokens per session scan A a20358d7147a

Subscribe to this mod's changes

lovable-boilerplate design.instructions.md is an instructions file published in the GitHub repository chihebnabil/lovable-boilerplate (65 stars, last pushed 1mo ago), licensed MIT. It adds 4,058 tokens to every session, about $0.0203 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.