generate

A UI prototype assembler that combines existing layout templates with design tokens to produce complete HTML and CSS prototypes.

In plain words
What is it for?
Use it after extracting a design system and layouts to combine them into page or component prototypes, optionally using referenced images.
Why use it?
It avoids recreating layout and styling decisions when those parts have already been extracted.

Command for Claude Code

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/catlog22/claude-code-workflow/generate
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

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 4,738 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 $0.00024 $0.04738
Opus 5 $0.00012 $0.02369
Sonnet 5 $0.00005 $0.00948
Haiku 4.5 $0.00002 $0.00474

Measured 2d ago against content hash 708ca1d4e631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate 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 2d 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/workflow/ui-design/generate.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate UI Prototypes (/workflow:ui-design:generate)

Overview

Pure assembler that combines pre-extracted layout templates with design tokens to generate UI prototypes (style × layout × targets). No layout design logic - purely combines existing components.

Strategy: Pure Assembly

  • Input: layout-*.json files + design-tokens.json (+ reference images if available)
  • Process: Combine structure (DOM) with style (tokens)
  • Output: Complete HTML/CSS prototypes
  • No Design Logic: All layout and style decisions already made
  • Automatic Image Reference: If source images exist in layout templates, they're automatically used for visual context

Prerequisite Commands:

  • /workflow:ui-design:style-extract → Complete design systems (design-tokens.json + style-guide.md)
  • /workflow:ui-design:layout-extract → Layout structure

Execution Process

Input Parsing:
   ├─ Parse flags: --design-id, --session
   └─ Decision (base path resolution):
      ├─ --design-id provided → Exact match by design ID
      ├─ --session provided → Latest in session
      └─ No flags → Latest globally

Phase 1: Setup & Validation
   ├─ Step 1: Resolve base path & parse configuration
   ├─ Step 2: Load layout templates
   ├─ Step 3: Validate design tokens
   └─ Step 4: Load animation tokens (optional)

Phase 2: Assembly (Agent)
   ├─ Step 1: Calculate agent grouping plan
   │  └─ Grouping rules:
   │     ├─ Style isolation: Each agent processes ONE style
   │     ├─ Balanced distribution: Layouts evenly split
   │     └─ Max 10 layouts per agent, max 6 concurrent agents
   ├─ Step 2: Launch batched assembly tasks (parallel)
   └─ Step 3: Verify generated files

Phase 3: Generate Preview Files
   ├─ Step 1: Run preview generation script
   └─ Step 2: Verify preview files

Phase 1: Setup & Validation

Step 1: Resolve Base Path & Parse Configuration

# Determine base path with priority: --design-id > --session > auto-detect
if [ -n "$DESIGN_ID" ]; then
  # Exact match by design ID
  relative_path=$(find .workflow -name "${DESIGN_ID}" -type d -print -quit)
elif [ -n "$SESSION_ID" ]; then
  # Latest in session
  relative_path=$(find .workflow/active/WFS-$SESSION_ID -name "design-run-*" -type d -printf "%T@ %p\n" 2>/dev/null | sort -nr | head -1 | cut -d' ' -f2)
else
  # Latest globally
  relative_path=$(find .workflow -name "design-run-*" -type d -printf "%T@ %p\n" 2>/dev/null | sort -nr | head -1 | cut -d' ' -f2)
fi

# Validate and convert to absolute path
if [ -z "$relative_path" ] || [ ! -d "$relative_path" ]; then
  echo "❌ ERROR: Design run not found"
  echo "💡 HINT: Run '/workflow:ui-design:list' to see available design runs"
  exit 1
fi

base_path=$(cd "$relative_path" && pwd)
bash(echo "✓ Base path: $base_path")

# Get style count
bash(ls "$base_path"/style-extraction/style-* -d | wc -l)

# Image reference auto-detected from layout template source_image_path

Read the full file on GitHub · 505 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. 2d ago First seen · 505 lines · 0 tokens per session scan A 708ca1d4e631

Subscribe to this mod's changes

generate is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 4,738 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.