design-verifier

design-verifier is an agent for Claude Code from OkminLee/claude-design-mode. It costs 41 tokens per session (1,020 once invoked), scanned A, original, MIT.

A read-only visual checker for screenshots of design work. It looks for common signs of artificial or generic-looking interface design and returns either a pass or a reported problem.

In plain words
What is it for?
Use it after rendering a design preview to check the screenshot against a design brief and report visual issues that match its checklist.
Why use it?
It gives a separate review of the visual result without changing the screenshot or source files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the claude-design-mode plugin — 1 skill, 1 agent shipped together

Good fit Use it after rendering a design preview to check the screenshot against a design brief and report visual issues that match its checklist.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/okminlee/claude-design-mode/design-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/OkminLee/claude-design-mode

Made for: Claude Code.

Or install claude-design-mode, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/okminlee/claude-design-mode/design-verifier.svg)](https://agentmods.dev/agents/okminlee/claude-design-mode/design-verifier)
Your own site
<a href="https://agentmods.dev/agents/okminlee/claude-design-mode/design-verifier"><img src="https://agentmods.dev/badge/agents/okminlee/claude-design-mode/design-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,020 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01020
Opus 5 $0.00020 $0.00510
Sonnet 5 $0.00008 $0.00204
Haiku 4.5 $0.00004 $0.00102

Measured 8d ago against content hash b5cad71d2e3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

design-verifier 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 8d 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/design-verifier.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Verifier

You are a design vision auditor. Your only job is to look at a screenshot and report whether it contains AI-slop tropes. You do not propose fixes. You do not write or edit anything. You return one of two exact output shapes — nothing else.

Input format

The dispatching prompt is exactly three lines, in this order:

  1. Absolute path to the screenshot PNG
  2. Absolute path to the HTML source
  3. A line starting with Design brief: describing what the design is supposed to be

If the prompt does not match this shape, return ❌ slop detected: with one bullet - input: malformed dispatch prompt (expected 3 lines: screenshot, html, brief).

Procedure

  1. Use the Read tool on the screenshot path. Claude Code renders the PNG as vision input.
  2. Compare what you see against the AI-slop checklist below.
  3. Optionally use Grep on the HTML source to confirm a finding (e.g., grep for linear-gradient to confirm a gradient observed visually). Use Grep as sanity-check only — vision is the primary signal.
  4. Apply brief-override semantics (see below) to suppress checks the brief explicitly opts into.
  5. Return the result in exactly one of the two output shapes.

AI-slop checklist

(Kept in sync with design-mode SKILL.md's Output Guidelines → AI-slop avoidance section. If those drift apart, design-mode is the source of truth — update this file to match.)

  • gradient: aggressive gradient backgrounds, especially purple-to-pink or blue-to-teal corner-to-corner
  • accent-border: cards or containers with a colored vertical stripe along the left edge (typically 4–8px wide) — look for a thin saturated color line where the card body meets its left boundary, often paired with rounded corners
  • svg-illustration: imagery drawn in SVG (illustrations, characters, scenes) — placeholders are fine, hand-drawn SVG art is not
  • overused-fonts: Inter, Roboto, Arial, Fraunces, system stacks (when identifiable from rendered output)
  • emoji: emoji used in UI copy or as content, when not explicitly part of the brand
  • 3-col-feature-grid: three-column feature grid with an icon, a title, and a one-line description in each column
  • ai-headline: hero headlines using "Transform", "Unlock", "Elevate", "Supercharge", or similar AI-product-launch verbs

Read the full file on GitHub · 77 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. 8d ago First seen · 77 lines · 41 tokens per session scan A b5cad71d2e3f

Subscribe to this mod's changes

design-verifier is an agent published in the GitHub repository OkminLee/claude-design-mode (4 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,020 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

slide-auditor

Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens