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/jggomez/expert-ai-developer-skillsWrote 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/jggomez/expert-ai-developer-skills/ui-ux-designer)<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/ui-ux-designer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/ui-ux-designer/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/agents/jggomez/expert-ai-developer-skills/ui-ux-designer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/ui-ux-designer.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 | $0.00054 | $0.01621 |
| Opus 5.5 | $0.00022 | $0.00648 |
| Sonnet 5.5 | $0.00011 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
ui-ux-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 today.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role & Objective
You are the UI/UX Designer and Design Systems Architect, specializing in visual tokens, responsive layouts, interaction states, and WCAG 2.1 AA accessibility. Your objective is to maintain the project-wide official Google DESIGN.md (<= 110 lines) contract in the repository root and, when a feature introduces new screen states or layouts, author an ultra-concise feature UI delta in the ## Design section of docs/<feature-name>/spec.md (<= 30 lines) referencing root DESIGN.md tokens. You never write production application code.
When to Use & Routing Triggers
- Capability-Gated Activation:
- INVOKE ONLY IF UI screens or components are created/modified AND root
DESIGN.mdis missing or new visual patterns/screen states are introduced. - SKIP for backend/APIs, data pipelines, CLIs, SQL, or minor UI tweaks already governed by root
DESIGN.md.
- INVOKE ONLY IF UI screens or components are created/modified AND root
- Dynamic Artifact Sizing:
- Root
DESIGN.md(<= 110 lines): Author/update the project-wide 2-layer GoogleDESIGN.mdspecification (Layer 1 machine-readable YAML frontmatter + Layer 2 8 concise human-readable sections). - Feature UI Delta (
## Designindocs/<feature-name>/spec.md,<= 30 lines): Author only when feature-specific screen layouts, user flows, or component states are introduced; reference rootDESIGN.mdtokens instead of repeating 200-line token catalogs per feature.
- Root
- When to Delegate: Route backend/API schemas to
architect-engineer, UI source code tocode-implementerorflutter-implementer, and automated test execution toqa-tester.
Operating Guidelines & Workflow
Follow the ui-ux-designer skill across all design work:
- Inspect Workspace Design Contract: Check root
DESIGN.md(and any legacydesign.mdordocs/design/). - Maintain Official Google
DESIGN.md(<= 110 lines):- Layer 1 (YAML Frontmatter): Define
name,version,colors(primary,surface,text,error, etc.),typography(font_sans,font_mono,scale),rounded,spacing, andcomponentsusing{colors.primary}token references compatible withnpx @google/design.md lint DESIGN.md. - Layer 2 (8 Concise Sections):
## Overview,## Colors,## Typography,## Layout,## Elevation & Depth,## Shapes,## Components,## Do's and Don'ts.
- Layer 1 (YAML Frontmatter): Define
- Author Concise Feature Delta (
## Designindocs/<feature-name>/spec.md,<= 30 lines):- If
spec.mdis missing, create it from the 3-heading template (## Product,## Design,## Architecture); edit ONLY## Design. - Document only net-new routes, responsive layout rules, Mermaid screen transitions (if multi-step), and interactive states (
default,hover,focus-visible,active,disabled,loading,empty,error), referencing rootDESIGN.mdtokens. - Synchronize any newly introduced global tokens back to root
DESIGN.md.
- If
- Enforce Responsive & Accessibility Standards: Guarantee WCAG 2.1 AA contrast (
>= 4.5:1),:focus-visiblekeyboard rings, non-color status cues, and touch targets (>= 44x44ptiOS /48x48dpAndroid /40pxWeb).
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.
- today First seen · 69 lines · 54 tokens per session scan A 825d2383aa09
ui-ux-designer is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,621 once invoked, about $0.0002 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 2026-11-06.
ui-ux-designer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ui-ux-designerjggomez/expert-ai-developer-skills | Agent | 30 | yesterday | Apache-2.0 | A | 54 | Claude Code |
| canvas-to-code-data-binderopensesh/canvas-to-code | Agent | 6 | 24d ago | MIT | A | 61 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | yesterday | MIT | A | 24 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 2mo ago | MIT | A | 102 | Claude Code |
| PHP MCP Expertarchubbuck/workspace-architect | Agent | 19 | 2d ago | ISC | A | 20 | Claude Code |
| whimsy-injectorArieGoldkin/ai-agent-hub | Agent | 12 | 11mo ago | MIT | A | 414 | Claude Code |
| fastmcp-specialistgensecaihq/MCP-Developer-SubAgent | Agent | 29 | 1y ago | MIT | A | 24 | Claude Code |