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 duonglkh/claude-android --skill agp-upgradegit clone --depth 1 https://github.com/duonglkh/claude-androidWrote 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/duonglkh/claude-android/agp-upgrade)<a href="https://agentmods.dev/skills/duonglkh/claude-android/agp-upgrade"><img src="https://agentmods.dev/badge/skills/duonglkh/claude-android/agp-upgrade/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/duonglkh/claude-android/agp-upgrade"><img src="https://agentmods.dev/badge/skills/duonglkh/claude-android/agp-upgrade.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 | $0.00073 | $0.01234 |
| Opus 5 | $0.00036 | $0.00617 |
| Sonnet 5 | $0.00015 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00123 |
Grade A, and why
agp-upgrade 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 9d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agp-upgrade
Guide Claude through an AGP version upgrade for the current Android project, using the
claude-android MCP server to read project context.
When this skill applies
The user asks anything like:
- "Upgrade AGP from 8.5 to 8.7"
- "I want to migrate to AGP 9"
- "What needs to change to bump AGP?"
- "Show me the AGP upgrade plan for this project"
Required tool — the MCP server must be registered
This skill calls into the claude-android MCP server. If the server is not registered with
Claude Code, instruct the user to run:
npm install -g @duonglkh/claude-android
claude mcp add android claude-android-mcp
Then verify with claude mcp list. The server name should be android.
Workflow
Follow these steps in order. Do not skip.
1. Read project context
Call mcp__android__get_project_info with projectPath = the absolute path to the project
root (where settings.gradle.kts lives). Use pwd or ask the user to confirm if uncertain.
Capture from the result:
agpVersion(current)kotlinVersionmoduleslistisKmp(KMP projects have extra steps)hasBuildLogic(convention plugins → upgrade them too)
If agpVersion is null, the project is not on a modern catalog — warn the user and ask
where AGP is declared.
2. Ask target AGP version
If the user has not specified, ask:
"Bạn muốn upgrade lên AGP version nào? Latest stable is X.Y.Z as of . Reply with version or 'latest'."
Look up the latest stable in the Android Gradle Plugin release notes (https://developer.android.com/build/releases/gradle-plugin) — do not guess.
3. Identify breaking changes between current and target
For each major / minor step between current and target, scan the official upgrade assistant notes:
Categorize each change as:
- Required (build will fail without it)
- Deprecation (works now, breaks later)
- Recommended (best practice but optional)
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.
- 9d ago First seen · 146 lines · 73 tokens per session scan A 5004105328c3
agp-upgrade is a skill published in the GitHub repository duonglkh/claude-android (0 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,234 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
android-studio
Operational skill for Android Studio: Gradle projects, emulators, Logcat, build variants, signing configs, and AGP troubleshooting.
android-playstore-builder
Build, sign, and publish Android apps to Google Play Store. Covers AAB builds, signing configs, Play Console, staged rollouts, and automated CI/CD.
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically…
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
app-store-preflight-compliance
Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.