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/jhostalek/dotclaude/uxnpx skills add JHostalek/dotclaude --skill uxgit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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/jhostalek/dotclaude/ux)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/ux"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/ux.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 | $0.00024 | $0.00309 |
| Opus 5 | $0.00012 | $0.00154 |
| Sonnet 5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
ux 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 4d 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.
What it actually says
page_path = $ARGUMENTS
page_path provided → focus on that page/component. Otherwise evaluate entire application UI.
Approach
Match evaluation depth to scope: single component → the 2-3 most relevant dimensions; full page → every applicable fundamental; entire app → 3 highest-traffic flows first (a whole-app sweep produces more findings than anyone acts on). Every applicable fundamental gets evaluated even when another lens overlaps it.
Gather context from at least one source, in order of preference: live browser navigation, screenshots, code review. Combine when available.
Apply the dimensions below.
!cat "${CLAUDE_SKILL_DIR}/ui-evaluation.md"
Output
Scores
Rate each evaluated dimension 1-5 (1=broken, 5=excellent). Compact table. Overall UX score = average.
Findings
Critical (blocks primary task): Issue → file:line → specific fix
High (major frustration): Issue → location → fix
What Works: Preserve these during fixes
Low (polish): Brief list
Validation
For each critical/high fix: what to test (user action) and what success looks like (behavior or outcome).
After presenting, offer to implement the top 3 critical/high fixes. Change nothing before the user accepts.
What ships with it
1 file 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.
- 4d ago First seen · 39 lines · 24 tokens per session scan A 2fce2415cb90
ux is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 24 tokens to every session and 309 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
peekaboo
Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…
electron-playwright-validator
This skill should be used when a user asks to launch, inspect, automate, test, validate, or debug an Electron desktop UI through Playwright/CDP, including blank renderers, runtime import failures, accessibility snapshots, layout defects, click-through flows, or post-change checks. Not for native macOS or mobile apps…
testing
· Write/debug tests: unit, integration, E2E, TDD, mocks, fixtures, a11y, perf. Triggers: 'test', 'spec', 'TDD', 'playwright', 'vitest', 'jest', 'pytest', 'coverage', 'flaky'. Not for security tests (use security-audit).
factory-design
Design-system discipline distilled across builds. Semantic token vocabulary (name intent, not palette position), CSS variables bridged into Tailwind, dark/light as a variable swap, single- vs two-layer token systems, component primitives as token consumers, when to promote a repeated utility cluster into a primitive…
factory-animation
Motion discipline distilled across builds. Attention as a fixed per-viewport budget, figure/ground separation (calm the ground, load motion into the figure), one focal point of motion per screen, diegetic-over-decorative test, trigger-on-intent-then-settle over perpetual loops, and the prefers-reduced-motion fallback.…
frontend-design
· Build/critique frontend UIs with taste, rejecting AI design tells. Mobile-first, touch-aware, dark+light. Triggers: 'frontend', 'ui', 'ux', 'css', 'tailwind', 'landing page', 'design review'. Not for code logic (code-review).