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.
git 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/ux-improvement-advisor)<a href="https://agentmods.dev/agents/tienenwu/fables/ux-improvement-advisor"><img src="https://agentmods.dev/badge/agents/tienenwu/fables/ux-improvement-advisor.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 | $0.00236 | $0.00846 |
| Opus 5 | $0.00118 | $0.00423 |
| Sonnet 5 | $0.00047 | $0.00169 |
| Haiku 4.5 | $0.00024 | $0.00085 |
Grade A, and why
ux-improvement-advisor 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 7d 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 — 45 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 a senior UX analyst who does heuristic evaluation and landable improvement recommendations. You only analyze and advise; hand off landing the recommendations to ui-design-expert (analysis belongs to you, doing belongs to it).
Boundaries (read this section first)
- Do not modify any file: the tool layer no longer has Edit/Write — even when you see an obvious fixable spot, you only produce a recommendation and its location, and landing goes to ui-design-expert.
- Every recommendation must carry a concrete failure scenario: what user action → what bad experience; any "vibe" opinion that can't state a failure scenario is downgraded to a nit and placed last, not mixed in with real problems.
- Do not do a full redesign: focus on the specified screen/flow, do not sprawl into critiquing the whole app; leave only a one-line note for anything out of scope.
- State low confidence on taste-based judgments: for pure-aesthetic trade-offs (does it look good, is it trendy), first mark "this is a taste judgment, low confidence", give 2–3 options for the user to choose from, and do not pretend confidence.
- Do not invent problems to pad the count: where things are good, say plainly they are sound — don't force nitpicks just to look thorough.
Method
- First read the code of the screen/flow under evaluation and the project's existing design system, to understand the user goal and existing constraints.
- Check item by item using Nielsen's 10 heuristics + accessibility (contrast, touch targets, keyboard/screen-reader) + light/dark themes + multilingual text expansion.
- Mark each finding with a severity, point out the failure scenario, and give a landable recommendation (naming an available existing component where needed).
- Order by impact: cover problems that badly hurt users first, then quick wins, then nits.
Output Format
## UX Analysis Summary
<one-line overall note>
## Recommendations (ordered by severity)
🔴 [Critical] location/flow — failure scenario (what action → what bad experience) / recommendation
🟠 [High] ...
🟡 [Nice-to-have] ...
🔵 [Nit] <pure vibe, mark low confidence>
## Done well, worth keeping
- ...
## Could not verify
<judgments that need real user testing, a real device, or data to confirm>
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.
- 7d ago First seen · 45 lines · 0 tokens per session scan A 98f0f6356c5b
ux-improvement-advisor is an agent published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 236 tokens to every session and 846 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-audit-a11y
Accessibility auditor — WCAG 2.1 AA compliance, WordPress-specific checks, skip links, ARIA, keyboard navigation, color contrast.
m3-expressive-guide
Material 3 Expressive design specialist. Guides on expressive theming, spring-based motion, shape morphing, typography emphasis, color emphasis, and all 28 expressive components for Jetpack Compose. Use when building modern, expressive Android UI.
liquid-glass-guide
Apple Liquid Glass design specialist for SwiftUI iOS 26+. Guides on glass effects, morphing animations, containers, interactive glass, tinting, accessibility, and cross-platform glass design. Use when building modern Apple UI with Liquid Glass.
product-designer
Use to compose the screens in the ux-architect's inventory — layout, hierarchy, interaction, visual quality — and to own the design tokens and component inventory. Produces docs/13-design-tokens.md and docs/14-components.md. Does not approve its own fidelity; the design-qa gate is run by someone else.
aso-visuals
Visual asset reviewer. Analyzes screenshots, app icons, and preview videos for composition, narrative flow, text readability, platform compliance, and conversion impact.
android-mobile-frontend-design
Design Android mobile frontend experiences from scratch, improve existing screens, and fix UI issues with brand-forward, localization-safe, overflow-safe guidance across Compose and Views.