Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JAICHANGPARK/workshop-harnessnpx agentmods add skills/jaichangpark/workshop-harness/android-workshop-builderWrote 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/jaichangpark/workshop-harness/android-workshop-builder)<a href="https://agentmods.dev/skills/jaichangpark/workshop-harness/android-workshop-builder"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/android-workshop-builder/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/jaichangpark/workshop-harness/android-workshop-builder"><img src="https://agentmods.dev/badge/skills/jaichangpark/workshop-harness/android-workshop-builder.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 | $0.00080 | $0.02516 |
| Opus 5.5 | $0.00032 | $0.01006 |
| Sonnet 5.5 | $0.00016 | $0.00503 |
| Haiku 4.5 | $0.00008 | $0.00252 |
Grade D, and why
android-workshop-builder scanned grade D with 3 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| **Linux (Ubuntu/Fedora)** | Android Studio / `android` CLI + KVM Acceleration | Missing `/dev/kvm` user permissions | Run `sudo usermod -aG kvm $USER` and reboot | Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| **macOS Apple Silicon (`arm64`)** | `curl -fsSL https://dl.google.com/android/cli/latest/darwin_arm64/install.sh \| bash` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **macOS Apple Silicon (`arm64`)** | `curl -fsSL https://dl.google.com/android/cli/latest/darwin_arm64/install.sh \| bash` | How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Hands-on Workshop Builder Skill
Purpose
Automates the creation of end-to-end technical hands-on workshops focused on Android Generative AI applications. Enforces modern Android development best practices including Jetpack Compose (Material 3), Gradle Kotlin DSL (build.gradle.kts), reactive state management with ViewModel and StateFlow, the unified Google GenAI Kotlin Android SDK (com.google.genai), and Google's official android CLI & Android Agent Skills.
Pre-Flight Web Research Protocol: Before generating Android workshop curriculum or code, verify the latest SDK versions for
com.google.genai:google-genai-kotlin-android(modern unified SDK, avoiding legacycom.google.ai.client.generativeai) and confirmandroidCLI commands viaandroid docsor official developer documentation.
🛠️ Google Android CLI & Skills Ecosystem Integration
Android hands-on workshops should actively utilize Google's android CLI and Android Agent Skills to streamline environment verification, headless emulator management, project scaffolding, and AI-assisted debugging:
1. android CLI Toolchain by OS
| Operating System & Architecture | Official One-Line Installation Command |
|---|---|
macOS Apple Silicon (arm64) |
curl -fsSL https://dl.google.com/android/cli/latest/darwin_arm64/install.sh | bash |
macOS Intel (x86_64) |
curl -fsSL https://dl.google.com/android/cli/latest/darwin_x86_64/install.sh | bash |
Linux (x86_64) |
curl -fsSL https://dl.google.com/android/cli/latest/linux_x86_64/install.sh | bash |
Windows (x86_64) |
curl -fsSL https://dl.google.com/android/cli/latest/windows_x86_64/install.cmd -o "%TEMP%\i.cmd" && "%TEMP%\i.cmd" |
2. Essential android CLI Workflow for Workshops
# 1. Initialize Android CLI environment & agent skills for project
android init
# 2. Install all official Google Android Agent Skills
android skills add --all
# 3. Verify connected devices & SDK configuration
android info
# 4. Manage Android Virtual Devices (AVD) headlessly
android emulator list
android emulator start <avd-name>
# 5. Search official Android Knowledge Base & Best Practices
android docs "Google GenAI SDK Kotlin Compose"
# 6. Build and run app on active device / emulator
android run
# 7. Inspect UI layout tree in JSON (fast headless debugging for AI agents)
android layout
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.
- today Changed 8fc5e9067cf8
- 1mo ago First seen · 227 lines · 80 tokens per session scan D 34d2effdb93b
android-workshop-builder is a skill published in the GitHub repository JAICHANGPARK/workshop-harness (5 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 2,516 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tipkit-generator
Generate TipKit infrastructure with inline/popover tips, rules, display frequency, and testing utilities. Use when adding contextual tips or feature discovery to an iOS/macOS app.
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and…
hr-mobile
Help HR managers, recruiters, and talent acquisition teams understand Mobile Development, iOS, Android, cross-platform engineering, mobile app architecture, and modern mobile ecosystems. Use when asked to explain mobile development, screen mobile developers, understand React Native or Flutter, compare native and…
3gpp-expert
3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment. Use whenever the user mentions: 3GPP, GSM, GPRS, EDGE, UMTS, WCDMA, HSPA, LTE, LTE-Advanced, 5G, NR, 5G-Advanced, 6G, NTN, RedCap, MIMO, beamforming, carrier aggregation, network…
explain
Explain how the IMG.LY SDK (CE.SDK) works: scenes, blocks, pages, fills, effects, timeline, rendering, export, asset sources, plugins. Use for "how does X work / why" questions about the engine or editor architecture.
xcode-26
Xcode 26 and Apple platform update notes with a focus on Liquid Glass, Foundation Models Framework, and Apple Intelligence. Use when asked to explain, summarize, compare, or implement Xcode 26 era framework changes across SwiftUI, UIKit, AppKit, Foundation, App Intents, StoreKit, MapKit, WidgetKit, visionOS, or Swift…