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/ahtavarasmus/lightfriend/userinterface-wikinpx skills add ahtavarasmus/lightfriend --skill userinterface-wikigit clone --depth 1 https://github.com/ahtavarasmus/lightfriendWrote 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/ahtavarasmus/lightfriend/userinterface-wiki)<a href="https://agentmods.dev/skills/ahtavarasmus/lightfriend/userinterface-wiki"><img src="https://agentmods.dev/badge/skills/ahtavarasmus/lightfriend/userinterface-wiki.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 | $0.00052 | $0.03537 |
| Opus 5 | $0.00026 | $0.01768 |
| Sonnet 5 | $0.00010 | $0.00707 |
| Haiku 4.5 | $0.00005 | $0.00354 |
Grade A, and why
userinterface-wiki 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 6d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
60 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.md 85 KB
- rules/_sections.md 3.2 KB
- rules/_template.md 418 B
- rules/a11y-reduced-motion-check.md 554 B
- rules/a11y-toggle-setting.md 508 B
- rules/a11y-visual-equivalent.md 674 B
- rules/a11y-volume-control.md 438 B
- rules/appropriate-confirmations-only.md 334 B
- rules/appropriate-errors-warnings.md 320 B
- rules/appropriate-no-decorative.md 347 B
- rules/appropriate-no-high-frequency.md 519 B
- rules/appropriate-no-punishing.md 478 B
- rules/container-callback-ref.md 701 B
- rules/container-guard-initial-zero.md 588 B
- rules/container-no-excessive-use.md 446 B
- rules/container-overflow-hidden.md 581 B
- rules/container-transition-delay.md 478 B
- rules/container-two-div-pattern.md 794 B
- rules/container-use-resize-observer.md 1.1 KB
- rules/context-cleanup-nodes.md 395 B
- rules/context-resume-suspended.md 455 B
- rules/context-reuse-single.md 524 B
- rules/design-filter-for-character.md 497 B
- rules/design-noise-for-percussion.md 544 B
- rules/design-oscillator-for-tonal.md 410 B
- rules/duration-max-300ms.md 347 B
- rules/duration-press-hover.md 372 B
- rules/duration-shorten-before-curve.md 411 B
- rules/duration-small-state.md 247 B
- rules/easing-entrance-ease-out.md 378 B
- rules/easing-exit-ease-in.md 353 B
- rules/easing-for-state-change.md 451 B
- rules/easing-linear-only-progress.md 390 B
- rules/easing-natural-decay.md 515 B
- rules/easing-no-linear-motion.md 521 B
- rules/easing-transition-ease-in-out.md 287 B
- rules/envelope-exponential-decay.md 383 B
- rules/envelope-no-zero-target.md 407 B
- rules/envelope-set-initial-value.md 418 B
- rules/exit-key-required.md 529 B
- rules/exit-matches-initial.md 490 B
- rules/exit-prop-required.md 595 B
- rules/exit-requires-wrapper.md 437 B
- rules/impl-default-subtle.md 280 B
- rules/impl-preload-audio.md 607 B
- rules/impl-reset-current-time.md 404 B
- rules/mode-pop-layout-for-lists.md 477 B
- rules/mode-sync-layout-conflict.md 589 B
- rules/mode-wait-doubles-duration.md 480 B
- rules/morphing-aria-hidden.md 358 B
- rules/morphing-consistent-viewbox.md 446 B
- rules/morphing-group-variants.md 922 B
- rules/morphing-jump-non-grouped.md 581 B
- rules/morphing-reduced-motion.md 644 B
- rules/morphing-spring-rotation.md 516 B
- rules/morphing-strokelinecap-round.md 323 B
- rules/morphing-three-lines.md 537 B
- rules/morphing-use-collapsed.md 511 B
- rules/native-backdrop-styling.md 497 B
- rules/native-placeholder-styling.md 515 B
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.
- 6d ago First seen · 254 lines · 52 tokens per session scan A 663ccc340e7e
userinterface-wiki is a skill published in the GitHub repository ahtavarasmus/lightfriend (78 stars, last pushed yesterday), licensed AGPL-3.0. It adds 52 tokens to every session and 3,537 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 2026-08-30.
Other skills, from other repositories
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
ui-html-renderer
Use this specialist for unusually complex stateful HTML, blank/runtime-risk repair, strict source-to-HTML fidelity, reusable component galleries, brand boards, or detailed implementation handoff. Ordinary single-page HTML uses ui-design-executor, which already preserves HTML-default delivery and baseline…
product-ui
Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.
impeccable
Use when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable references and an optional upstream detector CLI.
panel-app-react-vite-creator
Create or update an engineering-style NextClaw Panel component with pnpm, Vite, React, TypeScript, and Tailwind CSS, then build it into a static .panel directory inside a schema v2 package or an explicitly loose workspace Panel. Use for modern, reusable, complex, Agent-powered, typed Panel interfaces.
landing-page-generator
Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos.