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 commands/sukirman1901/frontend-expert/uigit clone --depth 1 https://github.com/sukirman1901/frontend-expertWrote 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/commands/sukirman1901/frontend-expert/ui)<a href="https://agentmods.dev/commands/sukirman1901/frontend-expert/ui"><img src="https://agentmods.dev/badge/commands/sukirman1901/frontend-expert/ui.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 | $0.00029 | $0.00527 |
| Opus 5 | $0.00015 | $0.00264 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
ui 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
Invoke the ui-developer agent.
Skills to load (in order)
frontend-judgment— non-trivial / blank-canvas only (see skip rules)design-tokensmarketing-landing— if marketing homepage / landing (hand-roll section stack)app-shell-routing— if shell / routing / dashboard / settingsdata-fetching— if async API UIforms-validation— if formsui-componentsresponsive-ui— MUST for layout (all devices; drawer+backdrop)motion— light shell defaults; marketing → families/patterns (motion-families.md) hand-rollanti-ai-slopui-feelaccessibility(light pass)fe-seo/webgl— only if in scope
Modes
/ui— token mode: walk decision tree inreferences/token-preset-scoring.md/ui --token <file>— force a specific token preset (explicit branch)/ui --custom— project's existing design system (custom branch)
$ARGUMENTS selects the mode and options.
What to do
- Choose direction via
frontend-judgmentwhen the UI is non-trivial / blank-canvas (2–3 approaches); skip for tiny clear fixes - Choose tokens via decision tree (custom → explicit → Plasma hard-gate → score)
- Shell: logo + utilities + theme in topbar; avatar → account menu; mobile drawer+backdrop; desktop sidebar collapse; custom selects for filters
- Marketing landings: load
marketing-landing— section stack (not hero-only); hand-roll, no registry install - Implement with composition, loading/error/empty states, responsive-ui, motion (shell light or named families)
- Make interactive elements keyboard accessible
- Scan for AI aesthetic patterns (incl. motion spam / hero-only), then apply
ui-feelcraft - Report: implementation, tokens used, Conventions check (Reicon/tokens/states/responsive/shell/landing/motion), a11y notes
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 · 41 lines · 29 tokens per session scan A 2159da7884d8
ui is a command published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 527 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 commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
template-ui
Design a Sent template-builder interface.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
review
執行 Figma vs 網頁的視覺比對審查，產出像素級 diff 報告和 AI 視覺判斷。.