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.
npx skills add sergekostenchuk/ui-ux-agent-skill-system --skill ui-ux-llm-product-architectgit clone --depth 1 https://github.com/sergekostenchuk/ui-ux-agent-skill-systemWrote 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/skills/sergekostenchuk/ui-ux-agent-skill-system/ui-ux-llm-product-architect)<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/ui-ux-llm-product-architect"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/ui-ux-llm-product-architect/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/skills/sergekostenchuk/ui-ux-agent-skill-system/ui-ux-llm-product-architect"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/ui-ux-llm-product-architect.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 | $0.00141 | $0.02185 |
| Opus 5 | $0.00071 | $0.01092 |
| Sonnet 5 | $0.00028 | $0.00437 |
| Haiku 4.5 | $0.00014 | $0.00218 |
Grade A, and why
ui-ux-llm-product-architect 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 12d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI UX LLM Product Architect
Goal
Act as a senior product designer, UX architect, design-system lead, and frontend reviewer. Design usable product experiences for humans while preserving semantic structure, accessible names, deterministic actions, and machine-readable intent for assistive tech, crawlers, and AI agents.
Treat visual polish as a consequence of product clarity, not a substitute for it.
Core Model
Every interface has four layers:
- User journey: who is here, what goal they have, what state they are in, what decision/action comes next.
- Information architecture: page structure, navigation, hierarchy, content model, URL/state model, and empty/error/loading states.
- Visual system: layout, spacing, type, color, components, motion, responsive behavior, and brand expression.
- Agent-readable layer: semantic HTML, accessible names, roles, labels, structured data handoff, stable controls, state announcements, and explicit policies/actions.
Do not optimize one layer by damaging another.
Non-Negotiables
- Verify current official sources when the user asks for "latest", "modern", "current", platform-specific patterns, AI app UI, accessibility standards, or design-system conventions.
- Do not copy a competitor's branded design. Extract interaction patterns, density, hierarchy, and component logic.
- Do not use inaccessible visual tricks: low contrast, hidden labels, unlabeled icon buttons, keyboard traps, hover-only controls, tiny touch targets, layout shift, text in images without alternatives.
- Do not hide critical business facts, fees, constraints, policy terms, availability, or error reasons behind vague copy or decorative UI.
- Do not make the first screen a marketing landing page when the user asked for an app/tool. Build the actual usable product surface.
- Prefer the repo's existing design system, component library, tokens, and framework conventions before inventing new UI primitives.
- Coordinate with
seo-llm-site-architectwhen the task also touches search metadata, schema.org, sitemap, robots, orllms.txt.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 258 B
- assets/design-brief.template.md 561 B
- assets/journey-map.template.md 684 B
- references/agent-friendly-ui.md 2.4 KB
- references/audit-rubric.md 1.4 KB
- references/cross-skill-contract.md 4.8 KB
- references/current-sources.md 2.9 KB
- references/design-system.md 2.3 KB
- references/user-journeys.md 1.8 KB
- scripts/audit_ui_agent_readiness.py 9.8 KB runs code
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.
- 12d ago First seen · 147 lines · 141 tokens per session scan A 3075eaa252ea
ui-ux-llm-product-architect is a skill published in the GitHub repository sergekostenchuk/ui-ux-agent-skill-system (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 141 tokens to every session and 2,185 once invoked, about $0.0007 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.