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 agentmods add skills/kreek/consult/ui-designnpx skills add kreek/consult --skill ui-designgit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/ui-design)<a href="https://agentmods.dev/skills/kreek/consult/ui-design"><img src="https://agentmods.dev/badge/skills/kreek/consult/ui-design.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 | $0.00024 | $0.01140 |
| Opus 5 | $0.00012 | $0.00570 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
ui-design 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Design
Iron Law
START FROM THE USER TASK AND HIERARCHY; EVERY ELEMENT EARNS ITS PLACE. WCAG 2.2 AA IS THE FLOOR.
When to Use
- Building, changing, or reviewing any user-facing UI surface: layout, components, design systems, typography, color, motion, responsive behavior, forms, navigation, modals, custom controls, interactive states. Simple forms, single-page apps, and "just basic styling" all qualify; the polished-product threshold is too high a bar.
- Testing keyboard flow, focus order, screen-reader behavior, contrast, reduced motion, forced colors, or accessible names.
When NOT to Use
- Backend API shape; use
api. - Frontend runtime debugging or tests only; pair with
proofand browser tooling. - Performance profiling beyond UI design choices; use
performance.
Rules
- One screen has one visually dominant primary action and an information order that survives a squint test. Remove elements that do not improve comprehension, trust, or action.
- Define the user task, state, and flow before choosing a framework, and choose existing framework or design-system patterns before inventing new ones.
- A small token system covers spacing, type, color, radius, and motion. No stray one-off values in committed CSS.
- Loading, empty, error, disabled, and success states are defined with the layout, not later.
- Accessibility is a design input, not a later review pass. Native HTML
controls and semantics come before ARIA:
<button type="button">for actions,<a href>for navigation,<nav>with links for site navigation,<dialog>with.showModal()for modals. Every interactive element has name, role, value, state, and keyboard behavior. - Focus is visible: at least a 2px outline at 3:1 contrast against both
adjacent surfaces, with a transparent fallback for Forced Colors. Tab
order follows DOM order; positive
tabindexhas no safe use. Focus is restored after a modal or overlay closes. - Color is never the only signal. Text and non-text contrast, target size, and reflow meet WCAG 2.2 AA. Reduced motion, forced colors, high contrast, and dark mode follow user preferences.
- Forms have explicit labels, grouped controls, errors tied to fields, and no placeholder-only instructions. Dragging has a single-pointer alternative. Authentication never depends on a cognitive test.
- Automated checks catch only part of the problem. Meaningful UI changes get manual keyboard testing, and custom controls, dialogs, menus, tabs, forms, and live updates get screen-reader testing. Remaining gaps are recorded as explicit blockers or deferred work, never left implicit.
What ships with it
7 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.
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.
- 2d ago Changed · +7 lines · +4 tokens per session d9b8b51a003f
- 5d ago First seen · 88 lines · 20 tokens per session scan A 90163662c675
ui-design is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,140 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 2026-08-31.
Other skills, from other repositories
clarify
Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's ## Clarifications section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this…
explain
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…
arch-review
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions. Auto-triggers when you say review this design, review this architecture, review this proposal, review my RFC, poke holes in this proposal, is this design sound, or critique this tech spec. Defers to…
pr-review
Team baseline for PR and code review — produces scope, blockers, nits, and strengths. Auto-triggers when you say review this PR, check this diff, review these changes, pre-review before I share, what do you think of this PR, or review the diff on this branch. Defers to any other installed skill whose description…
icon-composer-app-icon-workflow
Design, preview, validate, and integrate Apple app icons with Icon Composer. Use when a task mentions Icon Composer, .icon documents, Liquid Glass app icons, ictool preview exports, app icon design for iOS, iPadOS, macOS, or watchOS, or guided Icon Composer GUI work through Computer Use.
bootstrap-xcode-workspace
Create, adopt, extend, and align one Swift product workspace with app, extension, package, and service components under one permanent Xcode entrypoint.