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/yg2224/app-shell-ui/app-shell-uinpx skills add yg2224/app-shell-ui --skill app-shell-uigit clone --depth 1 https://github.com/yg2224/app-shell-uiWrote 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/yg2224/app-shell-ui/app-shell-ui)<a href="https://agentmods.dev/skills/yg2224/app-shell-ui/app-shell-ui"><img src="https://agentmods.dev/badge/skills/yg2224/app-shell-ui/app-shell-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 | $0.00174 | $0.05460 |
| Opus 5 | $0.00087 | $0.02730 |
| Sonnet 5 | $0.00035 | $0.01092 |
| Haiku 4.5 | $0.00017 | $0.00546 |
Grade A, and why
app-shell-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 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Shell UI
You are implementing App Shell UI: a reusable frontend design skill with two modes. Choose the surface before choosing pixels. Do not turn every request into a desktop shell, and do not turn every app into a generic marketing page.
Choose the surface first
| Mode | Use for | Default structure | Do not use for |
|---|---|---|---|
| App Mode | Logged-in tools, settings, consoles, chat, mail, workbenches, operational flows | Persistent left navigation + task canvas | Public marketing, reading, commerce, or portfolio surfaces |
| Website Mode | Marketing sites, product launches, portfolios, editorial pages, catalogues, docs, public content | A page-specific macrostructure selected from the user journey | A generic hero + three cards + CTA template, or a fake app shell |
If the request has both surfaces, design them separately: Website Mode for acquisition or public information, App Mode for the signed-in product. Share brand tokens where appropriate, but do not force the same layout or density across both.
Pre-flight (both modes)
Before making visual decisions in an existing project, inspect the route and its nearest
visual source of truth: current tokens, typography, theme mechanism, assets, framework,
component primitives, and installed icon/motion libraries. Preserve an established system
unless the user asks for a redesign. Check package.json before adding a dependency; do not
assume a library exists or mix two unrelated design systems in one surface.
If the brief is genuinely ambiguous between two materially different outcomes, ask exactly one short question. Otherwise state the inference in one sentence and continue. Do not turn a small implementation request into a requirements interview.
App Mode Workflow
- Pick a layout template (required before pixels):
- 设置型 — narrow left nav + form / toggle list
- 控制台型 — left nav + card grid / status list
- 工作台型 — session tree + centered empty state + composer card
- IM / 三栏型 — icon rail + list + detail
- Set the viewport budget — define the target desktop viewport (minimum 1280×800) and the one primary task for the route before adding content. See
references/layouts.md→ Viewport budget / 单页容量. - Lock dual-theme tokens — use
references/tokens.md(light + dark are both required by default). - Compose from recipes — use
references/components.md(nav item, card, list row, toggle, pill, empty/composer). Recipes are theme-agnostic; only variables change. - Implement with CSS variables +
data-theme="light"|"dark"; add a theme toggle; Tailwind/shadcn mapping optional. - Self-check — run the checklist at the end of this file in both themes and at the target viewport before delivery.
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 · 358 lines · 174 tokens per session scan A 3473eec3455b
app-shell-ui is a skill published in the GitHub repository yg2224/app-shell-ui (50 stars, last pushed 19d ago), licensed Apache-2.0. It adds 174 tokens to every session and 5,460 once invoked, about $0.0009 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
Shade ShadCN install
Guardrails for running pnpm dlx shadcn@latest add in Shade — never overwrite existing components, fresh branch first, swap raw colours for semantic tokens after integrating. Trigger when the user proposes a shadcn add, or when a fresh ShadCN-shaped file lands in apps/shade/src/components/ui.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
design-frontend-dev
Clean Impeccable frontend design skill. Use when the user wants to design, redesign, critique, audit, polish, harden, optimize, adapt, clarify, colorize, animate, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, onboarding, empty states…