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 Ghosteken/agent-harness --skill android-devgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWrote 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/ghosteken/agent-harness/android-dev)<a href="https://agentmods.dev/skills/ghosteken/agent-harness/android-dev"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/android-dev/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/ghosteken/agent-harness/android-dev"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/android-dev.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 | $0.00031 | $0.05252 |
| Opus 5.5 | $0.00012 | $0.02101 |
| Sonnet 5.5 | $0.00006 | $0.01050 |
| Haiku 4.5 | $0.00003 | $0.00525 |
Grade A, and why
android-dev 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 1mo 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.
This is a copy
100% identical to android-dev — 492 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 525 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android App Development Skill
Overview
This skill guides production-grade Android and cross-platform (non-iOS) app development following practices used at big tech companies. It covers the entire development lifecycle — architecture, UI, code quality, testing, error handling, release, and maintenance.
When to Use This Skill
- Use when deciding on a tech stack (see §1 Stack Selection)
- Use when setting up project architecture (see §2 Architecture)
- Use when designing UI, screens, or a design system (see §3 UI & Design)
- Use when ensuring code quality, patterns, or APIs (see Best Practices)
- Use when implementing error handling or debugging crashes (see §5 Error Handling)
- Use when planning testing strategy (see §6 Testing)
- Use when configuring build, CI/CD, or release pipelines (see §7 Build & Release)
- Use when optimizing performance or memory (see §8 Performance)
- Use when debugging or fixing bugs (see §9 Debugging)
- Use when following the full development roadmap (see §10 Development Roadmap)
- Use when needing deep reference for a stack (see
references/directory)
§1 Stack Selection
Choose based on team, requirements, and platform targets. Do not recommend iOS-specific paths.
Native Android — Kotlin + Jetpack Compose
Best for: Android-only apps, hardware-intensive features, best-in-class UX, new projects.
- Language: Kotlin
- UI: Jetpack Compose (modern declarative UI)
- Key libs: Room, Retrofit/Ktor, Hilt, WorkManager, DataStore, Navigation Compose
- Reference:
references/native-android.md
Native Android — Java + XML Views
Best for: Existing Java codebases, teams without Kotlin experience, legacy app maintenance, incremental Kotlin migration.
- Language: Java (fully supported by Google, not deprecated)
- UI: XML Layouts (ConstraintLayout, RecyclerView, ViewBinding)
- Key libs: Room, Retrofit, Hilt, WorkManager, LiveData, ViewModel
- Java and Kotlin coexist seamlessly in the same project — migrate incrementally
- Reference:
references/java-android.md
What ships with it
6 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.
- 1mo ago First seen · 525 lines · 31 tokens per session scan A 5d26aea482f9
android-dev is a skill published in the GitHub repository Ghosteken/agent-harness (4 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 5,252 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to android-dev, differing in 492 lines, and is treated as a copy.
Other skills, from other repositories
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…
capturing-proof
This skill should be used when the user asks to "capture proof", "record a demo of this feature", "make a video showing it works", "record the flow for the PR", "generate a PR body", "capture screenshots for the PR", "proof-capture", or when a verified feature needs PR-ready proof artifacts (video + numbered…
run-action
Explicit Codex workflow: Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as $rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with…
build-and-test
Explicit Codex workflow: Build the Expo/React Native app (local or EAS), install it, start Metro, then test a requested feature end-to-end.
check-env
Explicit Codex workflow: Check that the fenced React Native session, Metro, app target, and device inventory are ready for testing.
e2e
Run or author a Maestro E2E flow on an iOS simulator. Usage: /podium-mcp:e2e [ ].