MultiClaude: Command for Claude Code

.claude/commands/ipa/mockup-analyze.md

mockup-analyze is a command for Claude Code from nguyennguyenit/MultiClaude. It costs 10 tokens per session (3,898 once invoked), scanned A, original, MIT.

A command that examines HTML mockups and produces a UI design specification, including visual details and links between page elements and code patterns.

In plain words
What is it for?
Use it to inspect mockup HTML, capture desktop and mobile views, and document colors, fonts, spacing, effects, responsive behavior, and component mappings.
Why use it?
It turns visual mockups into written implementation guidance, reducing guesswork when rebuilding the design.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

This is nguyennguyenit/MultiClaude's own configuration. It tells Claude Code how to work on MultiClaude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MultiClaude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nguyennguyenit/MultiClaude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nguyennguyenit/MultiClaude/master/.claude/commands/ipa/mockup-analyze.md
Clone the repo
git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

Made for: Claude Code.

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 mockup-analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/mockup-analyze/github.svg)](https://agentmods.dev/commands/nguyennguyenit/multiclaude/mockup-analyze)
Your own site
<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/mockup-analyze"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/mockup-analyze/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.

agentmods 80×15 button for mockup-analyze

Your own site · 80×15
<a href="https://agentmods.dev/commands/nguyennguyenit/multiclaude/mockup-analyze"><img src="https://agentmods.dev/badge/commands/nguyennguyenit/multiclaude/mockup-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,898 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 $0.00010 $0.03898
Opus 5 $0.00005 $0.01949
Sonnet 5 $0.00002 $0.00780
Haiku 4.5 $0.00001 $0.00390

Measured 10d ago against content hash d9f75edb5a50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mockup-analyze 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 10d 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/ipa/mockup-analyze.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Generate UI_DESIGN_SPEC.md from HTML mockups using AI vision (Gemini) + HTML/CSS parsing.

Output: docs/UI_DESIGN_SPEC.md (design tokens, component mapping, responsive specs)


Input

Default: docs/UI-new-mock/ or docs/prototypes/


Role

You are a UI/UX Specification Engineer who:

  • Analyzes visual designs with pixel-perfect precision
  • Extracts design tokens (colors, typography, spacing, effects)
  • Maps HTML/CSS patterns to modern tech stacks
  • Ensures 100% implementation accuracy

Workflow

Step 1: Discover Mockup Files

# Find all HTML files in mockup directory
find <mockup-dir> -name "*.html" -type f

Validate:

  • At least 1 HTML file found
  • Files contain actual mockup content (not empty)

Step 2: Screenshot Each Mockup

Use Puppeteer or manual screenshots:

Option A: Automated (Puppeteer)

// Pseudocode - implement via Bash or Node script
for each HTML file:
  1. Open in headless browser
  2. Set viewport to 1920x1080 (desktop)
  3. Screenshot → /tmp/mockup-{N}.png
  4. Set viewport to 375x667 (mobile)
  5. Screenshot → /tmp/mockup-{N}-mobile.png

Option B: Manual

If Puppeteer unavailable:
1. AskUserQuestion: "Please screenshot each mockup file"
2. User provides screenshot paths
3. Continue with analysis

Step 3: AI Vision Analysis

For each screenshot, use ai-multimodal skill (Gemini):

Prompt for AI Vision:

Analyze this UI mockup screenshot and extract:

1. Color Palette:
   - Primary colors (CTAs, links, brand)
   - Secondary colors (accents, highlights)
   - Neutral colors (text, backgrounds, borders)
   - Semantic colors (success, warning, error)
   - For each color, provide hex value

2. Typography:
   - Font families (heading, body, monospace)
   - Font sizes (h1-h6, body, small)
   - Font weights (light, regular, medium, bold)
   - Line heights
   - Letter spacing

3. Spacing System:
   - Padding values (xs, sm, md, lg, xl)
   - Margin values
   - Gap values (flex/grid)
   - Consistent spacing scale (4px, 8px, 16px, etc.)

4. Border & Effects:
   - Border radius values
   - Border widths
   - Box shadows
   - Blur effects (glassmorphism, etc.)

5. Component Patterns:
   - Button styles (primary, secondary, ghost)
   - Input field styles
   - Card styles
   - Modal/dialog styles
   - Table styles
   - Navigation patterns

6. Layout Structure:
   - Grid system (columns, gaps)
   - Container max-widths
   - Sidebar width
   - Header height
   - Footer structure

7. Responsive Behavior:
   - Mobile breakpoint changes
   - Tablet breakpoint changes
   - Desktop-specific elements

Provide measurements in px, and suggest Tailwind CSS equivalents.

Read the full file on GitHub · 514 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. 10d ago First seen · 514 lines · 10 tokens per session scan A d9f75edb5a50

Subscribe to this mod's changes

mockup-analyze is a command published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 29d ago), licensed MIT. It adds 10 tokens to every session and 3,898 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 2026-08-30.