design

design is a command for Claude Code from sukirman1901/frontend-expert. It costs 24 tokens per session (545 once invoked), scanned A, original, MIT.

A command that runs a design review of a website or application. The review checks visual quality, design tokens, responsive layouts, accessibility, performance, and common AI-generated design problems.

In plain words
What is it for?
Auditing a full project, a specific component, or a token file, including responsive behavior, accessibility, motion, design fidelity, component states, and frontend performance.
Why use it?
It gives a structured check of the interface across devices and states, helping identify usability and visual issues before changes are made.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the frontend-expert plugin — 25 skills, 5 commands, 3 agents, 2 hooks shipped together

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 commands/sukirman1901/frontend-expert/design
Clone the repo
git clone --depth 1 https://github.com/sukirman1901/frontend-expert

Made for: Claude Code.

Or install frontend-expert, the plugin that ships this one along with the rest of its 25 skills, 5 commands, 3 agents, 2 hooks.

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 design

README.md
[![agentmods](https://agentmods.dev/badge/commands/sukirman1901/frontend-expert/design.svg)](https://agentmods.dev/commands/sukirman1901/frontend-expert/design)
Your own site
<a href="https://agentmods.dev/commands/sukirman1901/frontend-expert/design"><img src="https://agentmods.dev/badge/commands/sukirman1901/frontend-expert/design.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00024 $0.00545
Opus 5 $0.00012 $0.00272
Sonnet 5 $0.00005 $0.00109
Haiku 4.5 $0.00002 $0.00055

Measured 6d ago against content hash 8b5e2300e5cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.claude/commands/design.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoke the design-reviewer agent.

Skills to load (in order)

  1. anti-ai-slop
  2. ui-feel
  3. design-tokens (when a token file is available)
  4. responsive-ui — all-devices / breakpoint adherence
  5. accessibility
  6. web-performance
  7. ui-components as needed for pattern/state checks
  8. motion — when animated / marketing motion (family budget from motion-families.md; hand-roll)
  9. design-fidelity — when Figma/mock/screenshot is in scope
  10. fe-devtools — when measuring (Lighthouse/axe); never fabricate scores
  11. marketing-landing — when auditing marketing / landing pages
  12. frontend-judgment when recommending redesign directions
  13. frontend-testing — note coverage gaps as Info only

Modes

  • /design or /audit — full audit (default)
  • /design --quick — major issues only
  • /design --token <file> — audit against a specific token preset
  • /design --component <name> — audit one component

$ARGUMENTS selects the mode and options.

What to do

  1. Detect the project's framework / design system before recommending patterns
  2. Scan for AI aesthetic anti-patterns (incl. decorative motion spam / hero-only landing)
  3. Check ui-feel craft details
  4. Check token adherence when a token file is available
  5. Check responsive (320/768/1024/1440) + full-width CTA <768 — High if greenfield layout skips it
  6. Check shell chrome on dashboards (theme topbar, avatar menu, custom selects)
  7. Check marketing landing section stack when applicable (not hero-only; hand-roll)
  8. Check hierarchy + typography ladder when DOM/screenshots available
  9. Check motion family budget + reduced-motion when animation present
  10. Review accessibility against WCAG 2.1 AA
  11. Note performance risks relevant to UI (LCP/INP/CLS); use fe-devtools when measuring
  12. Output the design-reviewer scorecard (incl. Typography + Responsive + Motion + Landing) — mark unevaluated fields explicitly
  13. End with prioritized next moves (max 5)

Do not fabricate visual hierarchy or contrast scores without screenshots or token data.

Read the full file on GitHub · 49 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. 6d ago First seen · 49 lines · 24 tokens per session scan A 8b5e2300e5cc

Subscribe to this mod's changes

design is a command published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 545 once invoked, about $0.0001 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.