AG Kit is a toolkit that gives Google Antigravity coding agents a structured workspace with rules, skills, specialist agents, workflows, persistent memory, orchestration, MCP guidance, and a safety hook. It is for building and operating agent workflows in Antigravity, and its catalogue entries provide parts of that workspace contract.
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/vudovn/ag-kit/mobile-designnpx skills add vudovn/ag-kit --skill mobile-designgit clone --depth 1 https://github.com/vudovn/ag-kitWrote 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/vudovn/ag-kit/mobile-design)<a href="https://agentmods.dev/skills/vudovn/ag-kit/mobile-design"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/mobile-design.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 | $0.00047 | $0.03644 |
| Opus 5 | $0.00023 | $0.01822 |
| Sonnet 5 | $0.00009 | $0.00729 |
| Haiku 4.5 | $0.00005 | $0.00364 |
Grade A, and why
mobile-design 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 98% identical, 6 lines differ
- mobile-design — 97% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Design System
Philosophy: Touch-first. Battery-conscious. Platform-respectful. Offline-capable. Core Principle: Mobile is NOT a small desktop. THINK mobile constraints, ASK platform choice.
🔧 Runtime Scripts
Execute these for validation (don't read, just run):
| Script | Purpose | Usage |
|---|---|---|
scripts/mobile_audit.py |
Mobile UX & Touch Audit | python scripts/mobile_audit.py <project_path> |
🔴 MANDATORY: Read Reference Files Before Working!
⛔ DO NOT start development until you read the relevant files:
Universal (Always Read)
| File | Content | Status |
|---|---|---|
| mobile-design-thinking.md | ⚠️ ANTI-MEMORIZATION: Forces thinking, prevents AI defaults | ⬜ CRITICAL FIRST |
| touch-psychology.md | Fitts' Law, gestures, haptics, thumb zone | ⬜ CRITICAL |
| mobile-performance.md | RN/Flutter performance, 60fps, memory | ⬜ CRITICAL |
| mobile-backend.md | Push notifications, offline sync, mobile API | ⬜ CRITICAL |
| mobile-testing.md | Testing pyramid, E2E, platform-specific | ⬜ CRITICAL |
| mobile-debugging.md | Native vs JS debugging, RN DevTools, Logcat | ⬜ CRITICAL |
| mobile-navigation.md | Tab/Stack/Drawer, deep linking | ⬜ Read |
| mobile-typography.md | System fonts, Dynamic Type, a11y | ⬜ Read |
| mobile-color-system.md | OLED, dark mode, battery-aware | ⬜ Read |
| decision-trees.md | Framework/state/storage selection | ⬜ Read |
🧠 mobile-design-thinking.md is PRIORITY! This file ensures AI thinks instead of using memorized patterns.
Platform-Specific (Read Based on Target)
| Platform | File | Content | When to Read |
|---|---|---|---|
| iOS | platform-ios.md | Human Interface Guidelines, SF Pro, SwiftUI patterns | Building for iPhone/iPad |
| Android | platform-android.md | Material Design 3, Roboto, Compose patterns | Building for Android |
| Cross-Platform | Both above | Platform divergence points | React Native / Flutter |
What ships with it
13 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.
- decision-trees.md 16 KB
- mobile-backend.md 14 KB
- mobile-color-system.md 10.0 KB
- mobile-debugging.md 4.2 KB
- mobile-design-thinking.md 17 KB
- mobile-navigation.md 12 KB
- mobile-performance.md 19 KB
- mobile-testing.md 11 KB
- mobile-typography.md 10 KB
- platform-android.md 19 KB
- platform-ios.md 17 KB
- scripts/mobile_audit.py 35 KB runs code
- touch-psychology.md 16 KB
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 · 397 lines · 47 tokens per session scan A 8ecbbfe0b7db
mobile-design is a skill published in the GitHub repository vudovn/ag-kit (8,170 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 3,644 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.