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.
git clone --depth 1 https://github.com/Claude-Code-Community-Ireland/claude-code-resourcesWrote 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/commands/claude-code-community-ireland/claude-code-resources/design-ui)<a href="https://agentmods.dev/commands/claude-code-community-ireland/claude-code-resources/design-ui"><img src="https://agentmods.dev/badge/commands/claude-code-community-ireland/claude-code-resources/design-ui/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/commands/claude-code-community-ireland/claude-code-resources/design-ui"><img src="https://agentmods.dev/badge/commands/claude-code-community-ireland/claude-code-resources/design-ui.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 | $0.00017 | $0.00811 |
| Opus 5.5 | $0.00007 | $0.00324 |
| Sonnet 5.5 | $0.00003 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
design-ui 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic UI Designer
You are the entry point for the Agentic UI Designer system.
IMPORTANT: Use Ralph Loop for Best Results
For autonomous quality-gated iteration, use:
/ralph-loop "YOUR_DESIGN_BRIEF_HERE" --completion-promise "DESIGN_COMPLETE" --max-iterations 20
Example:
/ralph-loop "Create a landing page for a fintech startup - modern and trustworthy" --completion-promise "DESIGN_COMPLETE" --max-iterations 20
If Not Using Ralph Loop
You must manually implement the iteration loop:
Step 1: Initialize State
Create .claude/design-state.json:
{
"iteration": 1,
"minIterations": 5,
"maxIterations": 20,
"strategy": "Explore",
"bestScore": 0,
"gatesPassed": false,
"brief": "USER'S DESIGN BRIEF"
}
Step 2: Parse the Design Brief
Extract:
- Sector/industry (fintech, healthcare, e-commerce, SaaS)
- Target audience
- Style preferences (modern, minimal, bold)
- Special requirements (3D, realistic, space theme)
Step 3: Execute Design Loop
For EACH iteration:
- Research (iteration 1 or when pivoting):
Use WebSearch to gather:
- Sector UI patterns
- Competitor designs
- Color psychology for the industry
- Typography trends
- Generate:
Create files:
- index.html (semantic, accessible)
- styles.css (CSS custom properties, mobile-first)
- design-tokens.json
- Review - Evaluate against quality gates:
Check:
- Spatial design (grid, spacing, alignment)
- Color (contrast WCAG AA, harmony)
- Typography (hierarchy, readability)
- Originality (no vibe-code patterns)
- Update State:
Update .claude/design-state.json with:
- Current iteration
- Scores from review
- Issues to fix
- Whether gates passed
- Check Completion:
IF iteration >= 5 AND all gates pass:
Output: DESIGN_COMPLETE
ELSE:
Continue to next iteration
Step 4: Quality Gates (ALL must pass)
| Gate | Threshold |
|---|---|
| Minimum Iterations | >= 5 |
| Overall Score | >= 9.5/10 |
| WCAG AA | 100% |
| Vibe-Code | < 1% |
| Critical Issues | 0 |
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 · 144 lines · 17 tokens per session scan A 6b3a1c31e8f2
design-ui is a command published in the GitHub repository Claude-Code-Community-Ireland/claude-code-resources (11 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 811 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
erne-animate
ERNE — Implement animations using the ui-designer agent with Reanimated and Gesture Handler.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
design-audit
Audit the rendered design of live sites. Evidence capture first, then one critique per site. Argument is a URL, a repo name, or all.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.