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 skills add tuya/tuyaopen-ide-manifests --skill performance-ux-guardgit clone --depth 1 https://github.com/tuya/tuyaopen-ide-manifestsWrote 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/tuya/tuyaopen-ide-manifests/performance-ux-guard)<a href="https://agentmods.dev/skills/tuya/tuyaopen-ide-manifests/performance-ux-guard"><img src="https://agentmods.dev/badge/skills/tuya/tuyaopen-ide-manifests/performance-ux-guard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tuya/tuyaopen-ide-manifests/performance-ux-guard"><img src="https://agentmods.dev/badge/skills/tuya/tuyaopen-ide-manifests/performance-ux-guard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00211 | $0.02897 |
| Opus 5 | $0.00105 | $0.01448 |
| Sonnet 5 | $0.00042 | $0.00579 |
| Haiku 4.5 | $0.00021 | $0.00290 |
Grade A, and why
miniapp-performance-ux-guard 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 8d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- anti-patterns.md 6.0 KB
- build-guard.md 4.9 KB
- design-component.md 3.8 KB
- evals/evals.json 6.6 KB
- examples.md 10 KB
- launch-performance.md 2.7 KB
- references/app-css-variables.md 11 KB
- references/component-architecture.md 2.1 KB
- references/developer-quality-contract.md 2.1 KB
- references/miniapp-best-practices.md 3.9 KB
- references/miniapp-devtools-feedback.md 5.4 KB
- references/smart-ui-mapping.md 2.8 KB
- references/wiki-optimizations.md 4.3 KB
- review-gate.md 2.2 KB
- rubric.md 4.1 KB
- rules/a11y-aria-role.md 639 B
- rules/a11y-color-contrast.md 581 B
- rules/a11y-image-alt.md 642 B
- rules/a11y-touch-target.md 1.2 KB
- rules/anim-css-over-js.md 761 B
- rules/anim-no-setdata-in-frame.md 1.3 KB
- rules/anim-rjs-scroll-gesture.md 2.2 KB
- rules/code-no-hardcoded-chinese.md 3.3 KB
- rules/code-pattern-consistency.md 769 B
- rules/code-validation-evidence.md 761 B
- rules/content-error-message.md 629 B
- rules/content-loading-text.md 652 B
- rules/design-theme-css-vars.md 2.5 KB
- rules/form-input-type.md 628 B
- rules/form-keyboard-adapt.md 691 B
- rules/form-validation-timing.md 714 B
- rules/ix-async-chain.md 1.1 KB
- rules/ix-button-feedback.md 843 B
- rules/ix-duplicate-submit.md 1.1 KB
- rules/ix-empty-state.md 1.2 KB
- rules/ix-error-recovery.md 996 B
- rules/launch-cache-strategy.md 2.0 KB
- rules/launch-data-prefetch.md 6.4 KB
- rules/launch-dead-code-cleanup.md 683 B
- rules/launch-engine-capability.md 847 B
- rules/launch-global-injection.md 1.1 KB
- rules/launch-memory-cache.md 993 B
- rules/launch-package-budget.md 3.6 KB
- rules/launch-preload.md 700 B
- rules/launch-progressive-first-screen.md 1.2 KB
- rules/launch-public-dependency-cache.md 953 B
- rules/launch-remove-react-dom.md 735 B
- rules/launch-render-bridge-budget.md 1.0 KB
- rules/launch-resource-cdn.md 671 B
- rules/launch-skeleton-screen.md 661 B
- rules/launch-smart-ui-on-demand.md 736 B
- rules/launch-startup-heavy-compute.md 791 B
- rules/launch-sub-ui-config-prefetch.md 1.1 KB
- rules/launch-subpackage.md 763 B
- rules/launch-sync-api.md 1.6 KB
- rules/layout-custom-navbar.md 761 B
- rules/layout-safe-area.md 581 B
- rules/layout-scroll-penetration.md 693 B
- rules/list-incremental-render.md 742 B
- rules/list-scroll-throttle.md 855 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.
- 8d ago First seen · 121 lines · 211 tokens per session scan A 0efe5b452a42
miniapp-performance-ux-guard is a skill published in the GitHub repository tuya/tuyaopen-ide-manifests (2 stars, last pushed yesterday), with no licence file. It adds 211 tokens to every session and 2,897 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
codegen-react
Scaffold and iterate on Vite + React applications.
home-assistant-dashboard-ui
Build or change Home Assistant dashboards — Lovelace views, cards, layouts, themes, badges, custom cards and card-mod — and verify the result visually with a screenshot. Covers choosing between hab dashboard commands and YAML mode, the standard card set, conditional and template cards, and the screenshot verification…
pdf-press
Teaches agents how to generate Markdown, HTML (with embedded SVG), and Mermaid content that renders beautifully to multi-page PDF via writepdf, with proper page breaks, compact professional layouts, brand and domain-adaptive color schemes, multi-column support for scientific papers, magazine-style editorial documents…
legacy-circuit-mockups
Breadboard circuit mockups via HTML5 Canvas. Use when creating circuit layouts, visualizing 6502/retro electronics components, drawing breadboard diagrams, or designing vintage computer schematics with discrete parts.
go-bulma
Scaffold the Bulma CSS framework into a Go web app with embedded assets for zero-dependency binaries. Use when building an HTML UI with a classes-based CSS framework and no Node toolchain.
web-app-creator
Build webapps that integrate with Meta Aria Gen2 (Nebula) smart glasses, usable by any agent that supports skills (Manus, Claude Code, etc.). macOS only — the backend launcher and auto-open browser hooks are written for macOS; Windows and Linux are not supported. Covers the full Web App Creator stack: real-time sensor…