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 kelvinkosbab/AppBootstrapAI --skill android-design-system-progit clone --depth 1 https://github.com/kelvinkosbab/AppBootstrapAIWrote 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/kelvinkosbab/appbootstrapai/android-design-system-pro)<a href="https://agentmods.dev/skills/kelvinkosbab/appbootstrapai/android-design-system-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-design-system-pro/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/kelvinkosbab/appbootstrapai/android-design-system-pro"><img src="https://agentmods.dev/badge/skills/kelvinkosbab/appbootstrapai/android-design-system-pro.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 | $0.00121 | $0.01636 |
| Opus 5.5 | $0.00048 | $0.00654 |
| Sonnet 5.5 | $0.00024 | $0.00327 |
| Haiku 4.5 | $0.00012 | $0.00164 |
Grade A, and why
android-design-system-pro 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up or review the UI foundation of an Android app: icons, theme, tokens, and core components. This is the deep companion to the always-on android-iconography.md and android-design-system.md rules — the rules steer while writing; this skill scaffolds a :core:designsystem module from scratch or audits a whole app against one.
Applies to Jetpack Compose apps (with View-interop notes). Pick the mode from the request:
- Bootstrap — a new app, or an app with no design-system module: generate the module skeleton using
references/bootstrap.md, then fill the theme and components with the user's brand inputs (seed color, brand font, shape style, dynamic-color stance). Ask only for inputs you can't infer; default to a Material Theme Builder baseline with dynamic color on, and say so. - Audit — an existing app: find and rank what breaks dark theme, dynamic color, font scaling, RTL, TalkBack, edge-to-edge, and visual consistency; propose an incremental migration.
- Write/fix — make the changes directly and summarize them in the same file-by-file format.
Review process (audit mode):
- Inventory with the searches in
references/bootstrap.md("Audit searches") — literal colors, literal sizes,material-icons-extendedusage, drawable references from feature modules, clickable boxes, missing insets handling. Count before reading files; the counts set priorities. - Audit icons using
references/iconography.md— the icon source andAppIconsvocabulary, sizing/tint/mirroring, icon accessibility, launcher (adaptive + monochrome), notification and splash icons. - Audit theme and tokens using
references/theming-and-tokens.md—AppThemestructure, color roles and pairs, dynamic color, extended tokens via CompositionLocal, type/shape/spacing scales, edge-to-edge. - Audit components using
references/components.md— wrapper vs reimplementation, API shape (modifier, slots, Defaults objects), statelessness and stability, duplicates to converge, previews, the catalog, screenshot tests.
If doing a partial review, load only the relevant reference files.
Core Instructions
- Roles over values. Feature code reads
MaterialTheme.colorScheme.*,MaterialTheme.typography.*,AppTheme.spacing.*,AppIcons.*. A fix that replaces one literal with another literal is not a fix. - Material 3 first. Wrap M3 components and use M3 roles; reimplementing a component or inventing a parallel color system is maintenance the team pays on every Material upgrade. Recommend custom only where M3 has no equivalent, and then as an extension of the theme.
- Adaptation is the test. For every token and component ask: does it survive dark theme, dynamic color, 200% font scale, RTL, edge-to-edge, and TalkBack? Report the setting that breaks it.
- The design system is a module with a direction.
:core:designsystemdepends on Compose/Material only; features depend on it. Flag inverted dependencies (components importing ViewModels, repositories, or:datamodels). - Incremental, never big-bang. Migration plans move one screen or one token family at a time and keep the app shipping.
- Severity by user impact: broken (unreadable text in a theme, content under system bars, unlabeled icon-only control, white-square notification icon, clipped launcher icon, clickable box with no semantics) > inconsistent (duplicate components, off-scale spacing, mixed icon styles) > polish (expressive motion, tonal tuning).
- Cross-reference, don't duplicate: deep TalkBack/keyboard audits belong to
android-accessibility-pro; recomposition and stability deep-dives toandroid-compose-pro; size-class layouts toandroid-adaptive-layout-pro; module wiring toandroid-gradle-architecture-pro.
What ships with it
4 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.
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.
- 6d ago First seen · 90 lines · 121 tokens per session scan A cb5c4bccd382
android-design-system-pro is a skill published in the GitHub repository kelvinkosbab/AppBootstrapAI (7 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,636 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
kmp-glassmorphism-ui
Implements a production-grade Glassmorphism design system for Kotlin Multiplatform (KMP) Compose Multiplatform projects. Use when the user asks for glass UI, frosted glass effects, glassmorphism theme, translucent/transparent UI components, liquid/blob animated backgrounds, or premium modern dark-mode design in a…
figma-a11y-annotations
Rules for generating accessibility annotations on iOS/iPadOS mobile designs in Figma. Enforces a bare-minimum annotation discipline, an iOS vocabulary instead of web ARIA terms, and exact grammar for names, control types, page titles, values, hints, headings, groups, and reading order. Never annotates visible text as…
iOS SwiftUI Accessibility
Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 24 WCAG criteria.
compose-component-design
Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.
maui-accessibility
Improve MAUI accessibility. USE FOR: semantic labels, hints, headings, screen-reader focus/announcements, AutomationProperties, touch targets, decorative content, TalkBack/VoiceOver/Narrator checks. DO NOT USE FOR: general layout, automation-only tests, performance.
compose-screens-footguns
Compose screen and interaction traps: navigation, adaptive layout, window insets, pagers, toolbars, sheets, list drag and selection, sliders, text fields, settings UI, one-shot effects. Use when layout, gestures or navigation misbehave.