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 hoangatg/ai-agent-toolkit --skill frontend-designgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/frontend-design)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/frontend-design"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/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/hoangatg/ai-agent-toolkit/frontend-design"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03093 |
| Opus 5.5 | $0.00015 | $0.01237 |
| Sonnet 5.5 | $0.00007 | $0.00619 |
| Haiku 4.5 | $0.00004 | $0.00309 |
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 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.
This is a copy
97% identical to frontend-design — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design System
Philosophy: Every pixel has purpose. Restraint is luxury. User psychology drives decisions. Core Principle: THINK, don't memorize. ASK, don't assume.
🎯 Selective Reading Rule (MANDATORY)
Read REQUIRED files always, OPTIONAL only when needed:
| File | Status | When to Read |
|---|---|---|
| ux-psychology.md | 🔴 REQUIRED | Always read first! |
| color-system.md | ⚪ Optional | Color/palette decisions |
| typography-system.md | ⚪ Optional | Font selection/pairing |
| visual-effects.md | ⚪ Optional | Glassmorphism, shadows, gradients |
| animation-guide.md | ⚪ Optional | Animation needed |
| motion-graphics.md | ⚪ Optional | Lottie, GSAP, 3D |
| decision-trees.md | ⚪ Optional | Context templates |
🔴 ux-psychology.md = ALWAYS READ. Others = only if relevant.
🔧 Runtime Scripts
Execute these for audits (don't read, just run):
| Script | Purpose | Usage |
|---|---|---|
scripts/ux_audit.py |
UX Psychology & Accessibility Audit | python scripts/ux_audit.py <project_path> |
⚠️ CRITICAL: ASK BEFORE ASSUMING (MANDATORY)
STOP! If the user's request is open-ended, DO NOT default to your favorites.
When User Prompt is Vague, ASK:
Color not specified? Ask:
"What color palette do you prefer? (blue/green/orange/neutral/other?)"
Style not specified? Ask:
"What style are you going for? (minimal/bold/retro/futuristic/organic?)"
Layout not specified? Ask:
"Do you have a layout preference? (single column/grid/asymmetric/full-width?)"
⛔ DEFAULT TENDENCIES TO AVOID (ANTI-SAFE HARBOR):
| AI Default Tendency | Why It's Bad | Think Instead |
|---|---|---|
| Bento Grids (Modern Cliché) | Used in every AI design | Why does this content NEED a grid? |
| Hero Split (Left/Right) | Predictable & Boring | How about Massive Typography or Vertical Narrative? |
| Mesh/Aurora Gradients | The "new" lazy background | What's a radical color pairing? |
| Glassmorphism | AI's idea of "premium" | How about solid, high-contrast flat? |
| Deep Cyan / Fintech Blue | Safe harbor from purple ban | Why not Red, Black, or Neon Green? |
| "Orchestrate / Empower" | AI-generated copywriting | How would a human say this? |
| Dark background + neon glow | Overused, "AI look" | What does the BRAND actually need? |
| Rounded everything | Generic/Safe | Where can I use sharp, brutalist edges? |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 419 lines · 37 tokens per session scan A ec98e8f51a68
frontend-design is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 3,093 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to frontend-design, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
ux-ui
Use this agent when you need to design, audit, migrate, rewire, or rewrite UX/UI.
dynamic-typography
L2 mechanics for type in motion: variable-font axis animation, kinetic text, per-letter effects, scroll- and pointer-linked type, and typographic state transitions. Fires on implementing or auditing type-specific motion, or when chained from a higher layer. Ownership of motion budgets, timing doctrine, and…
plain-language-ui
Use this agent whenever building, adding, or redesigning any screen, form, page, dashboard, wizard, table, or component in a compliance/fintech/regtech app (AML, KYC, VAT, payroll, audit, CSSF, tax filing), whenever the user says labels are cryptic or confusing ("I don't understand this button/field"), or whenever…
refactoring-ui
Apply UI design principles from Refactoring UI by Adam Wathan & Steve Schoger. Covers visual hierarchy (size, weight, color, spacing), layout systems (spacing scales, grids), typography (type scales, line-height, alignment), color (HSL palettes, shade systems, accessible contrast), depth (shadow elevation, overlap)…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.