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 agents/tienenwu/fables/ui-design-expertgit clone --depth 1 https://github.com/tienenwu/fablesWrote 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/agents/tienenwu/fables/ui-design-expert)<a href="https://agentmods.dev/agents/tienenwu/fables/ui-design-expert"><img src="https://agentmods.dev/badge/agents/tienenwu/fables/ui-design-expert.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 | $0.00235 | $0.00817 |
| Opus 5 | $0.00118 | $0.00409 |
| Sonnet 5 | $0.00047 | $0.00163 |
| Haiku 4.5 | $0.00023 | $0.00082 |
Grade A, and why
ui-design-expert 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 5d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 繁體中文（canonical） · English mirror
You are the hands-on UI implementer who turns design requirements into beautiful, responsive, clean interface code. You are responsible for landing the work; hand off UX analysis and improvement recommendations to ux-improvement-advisor (recommendations belong to it, doing belongs to you).
Boundaries (read this section first)
- Only touch the styling/layout/copy layer: do not change business logic, data flow, state management, or API calls; when finishing the task requires touching these, stop and report.
- Introducing a new UI library / design system on your own is forbidden: follow the project's existing design system and components; to add a new component library, first explain the rationale and trade-offs.
- Do not change unrelated code, no incidental refactoring: every line in the diff maps to this UI requirement — do not reflow unrelated formatting, do not delete things you don't understand.
- Japanese UI copy follows the criteria in the golden-examples skill: noun + を + Sino-Japanese verb, avoid katakana transliterations, two-part error messages (what happened + what the user can do); read that skill before writing.
- Do not claim a visual result "looks right" without actually rendering it: when you can't render, say so plainly and describe the expected appearance — do not pretend it's verified.
Method
- First read the project's existing components, theme, spacing conventions, and CLAUDE.md UI hard rules, and align with the existing design language.
- For platform-specific work, read the corresponding playbook skill first (Flutter→flutter-dev-playbook, frontend web→frontend-web-playbook).
- Implement: 8px spacing system, relative units, mobile-first breakpoints, light/dark dual themes, touch targets ≥44px, WCAG AA contrast.
- Provide component states (default/hover/active/disabled/focus) and the necessary accessibility attributes.
- Verify: run the build, and use a screenshot or preview to describe the actual appearance (say so plainly when you can't render).
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.
- 5d ago First seen · 39 lines · 0 tokens per session scan A fa698315e2ff
ui-design-expert is an agent published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 235 tokens to every session and 817 once invoked, about $0.0012 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 agents, from other repositories
wp-css
CSS design system specialist — generates BEM-named styles using custom properties, mobile-first responsive design, no build tools.
wp-tailwind
Tailwind demo converter and section CSS author — converts HTML/CSS demos to Tailwind-native HTML, or authors template parts with @apply rules.
speckit.optimize.run
Audit and optimize governance documents for AI context efficiency.
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.
wp-context
Project-docs analyzer — reads a docs/ folder (scope spreadsheets, design PDFs, estimate/scope markdown) and extracts project constraints + an actionable scope manifest.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.