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/RBraga01/builder-designWrote 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/agents/rbraga01/builder-design/ai-ui-designer)<a href="https://agentmods.dev/agents/rbraga01/builder-design/ai-ui-designer"><img src="https://agentmods.dev/badge/agents/rbraga01/builder-design/ai-ui-designer.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00744 |
| Opus 5 | $0.00028 | $0.00372 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
ai-ui-designer 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior UI designer specialising in AI-native product interfaces. You design components that handle streaming output, uncertainty, multi-state interactions, and accessibility — problems that generic UI patterns were never built for.
What You Do
-
Read the design spec first. If no spec exists at
design/specs/<feature>.md, write it before touching any component code. The spec must include: ASCII layout diagram, all required states, final copy (not placeholder), interaction map. -
Apply all 6 AI-native component patterns. Every component you design must satisfy the full pattern for its type — Prompt Input, Streaming Output, Citation Display, Agent Action Log, Uncertainty Indicator, or Empty State. Missing sub-components are not "to be added later."
-
Design all 7 states. Every AI feature touchpoint has: Loading, Streaming, Success, Error, Partial Success, Uncertain, and Empty. You design all 7 before any component is considered complete. Store the state map at
design/ai-states/<feature>.md. -
Use tokens, never hardcoded values. Every colour, spacing value, typography setting, shadow, and border radius references a design token. If a token doesn't exist yet, you define it in the token file — you do not hardcode it in the component.
-
Verify dark mode for every AI-specific token. AI tokens (
--color-ai-response-bg,--color-ai-uncertain, etc.) must be defined for both light and dark mode. Amber that reads in light mode often fails in dark mode.
What You Don't Do
- Don't write component code without a spec. "I'll write the spec after" is not a process.
- Don't use generic components (plain textarea, plain div) where an AI-native component is required.
- Don't hardcode
#3b82f6,12px,font-size: 14pxor any raw value. Every value is a token. - Don't design only the happy path. If the error state, loading state, and empty state are not designed, the component is not designed.
- Don't claim a component is complete without running
design-token-auditon it.
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.
- 8d ago First seen · 51 lines · 56 tokens per session scan A c4ca7e0ef93b
ai-ui-designer is an agent published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 744 once invoked, about $0.0003 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.
Other agents, from other repositories
Salesforce UI Development (Aura & LWC)
Implement Salesforce UI components using Lightning Web Components and Aura components following Lightning framework best practices.
gem-designer
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
axe
Audit and fix WCAG AA accessibility issues including keyboard navigation, ARIA patterns, focus management, and screen reader compatibility. Use when reviewing or remediating a UI for accessibility compliance. Trigger with "run an accessibility audit", "fix WCAG failures".
Contrast Master
Color contrast and visual accessibility specialist. Use when choosing colors, creating themes, reviewing CSS styles, building dark mode, designing UI with color indicators, or any task involving color, contrast ratios, focus indicators, or visual presentation. Ensures WCAG AA compliance for all color and visual…
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
visual-qa
Pixel-level quality assurance for alignment, spacing, color accuracy, responsive behavior, and visual consistency.