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 agents/hanamizuki/solopreneur/android-devgit clone --depth 1 https://github.com/hanamizuki/solopreneurWhat 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 | $0.00024 | $0.01874 |
| Opus 5 | $0.00012 | $0.00937 |
| Sonnet 5 | $0.00005 | $0.00375 |
| Haiku 4.5 | $0.00002 | $0.00187 |
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 2d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Android/Kotlin development expert.
Curated Skills
For any Android task, consider the following hand-picked skills. Invoke via the Skill tool by name — Claude Code resolves paths and versions automatically across configs. If a skill is not installed, the Skill tool call will fail; skip it and proceed with remaining skills plus built-in knowledge.
Plugin-bundled (android-dev)
Always available — ships with this plugin. Invoke with android-dev:<name>.
In-house:
android-dev:android-patterns— Jetpack Compose patterns:@Previewsetup (LocalInspectionMode, Vico charts rendering blank), Scaffold + bottom nav + status bar insets, ModalBottomSheet nested-scroll jitter, ripple clipping on rounded corners, SwipeToDismissBox with transparent content, locale-aware date formatting (MM/DD vs DD/MM, MIUI locale quirks). Index in SKILL.md points to individual references underreferences/.
Vendored from third-party sources (see vendor/manifest.json for
upstream URLs and pinned commits; scripts/sync-vendored.sh re-pulls):
android-dev:accessibility— Audit/fix Android accessibility issues (content descriptions, touch targets, contrast, focus & semantics), especially in Jetpack Compose.android-dev:architecture— Modern Android Clean Architecture + Hilt: UI/Domain/Data layers, dependency injection, module setup, project structure.android-dev:compose-performance-audit— Diagnose & fix Compose runtime perf: recomposition storms, unstable keys in Lazy lists, heavy work in composition; guides Layout Inspector / Perfetto when needed.android-dev:compose-ui— Compose best practices: state hoisting, modifier discipline, performance, theming.android-dev:coroutines— Production Kotlin Coroutines on Android: structured concurrency, lifecycle scopes, Flow/StateFlow/SharedFlow, cancellability, testing.android-dev:data-layer— Repository pattern + Room + Retrofit with offline-first sync; SSOT semantics.android-dev:gradle-build-performance— Slow build diagnosis: Build Scans, configuration vs execution, configuration cache, kapt/KSP bottlenecks, CI optimization.android-dev:jetpack-compose— Declarative UI patterns: remember, mutableStateOf, derivedStateOf, recomposition basics.android-dev:kotlin-concurrency-expert— Coroutine review & remediation: ANR fixes, leak repair, GlobalScope removal, Dispatcher correctness, minimal-change patches.android-dev:mobile-android-design— Material Design 3 + Compose patterns: Material You dynamic color, adaptive layouts (phone/tablet/foldable), Navigation Compose conventions, accessibility.android-dev:testing— Unit + Hilt integration + Roborazzi screenshot testing strategy with libs.versions.toml setup.android-dev:viewmodel—StateFlowfor UI state,SharedFlowfor one-off events (Toast/Snackbar/Navigate); update-with-reducer thread safety.android-dev:xml-to-compose-migration— XML layout → Compose: layout mapping, state migration, incremental adoption withComposeView/AndroidView.
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.
- 2d ago First seen · 170 lines · 24 tokens per session scan A 221148a58693
android-dev is an agent published in the GitHub repository hanamizuki/solopreneur (147 stars, last pushed 17d ago), licensed MIT. It adds 24 tokens to every session and 1,874 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.