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/desquared/agents-rules-skills/android-agent-guidelinesgit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWhat 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 | $0.00000 | $0.01535 |
| Opus 5 | $0.00000 | $0.00767 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
android-agent-guidelines 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Agent Discovery & Implementation Guidelines
CRITICAL: All Android agents MUST execute a discovery scan before making ANY implementation decisions. No assumptions. No guessing. Align to what already exists.
1. Discovery-First Approach
Before writing code or proposing solutions, run a "Project Fingerprint" scan.
Phase A — Dependency Scan
Scan version catalogs and build files to identify the core tech stack:
# Preferred: check version catalog first
grep -rE "koin|hilt|dagger|room|realm|sqldelight|ktor|retrofit|coil|glide|compose|rxjava|coroutines" gradle/libs.versions.toml
# Fallback: scan build files directly
grep -rE "koin|hilt|dagger|room|realm|sqldelight|ktor|retrofit|coil|glide|compose|rxjava|coroutines" ./build.gradle*
Phase B — Architecture & Pattern Fingerprinting
Identify whether the project is standard Android or KMP, then find existing patterns:
# KMP vs Standard Android
find . -maxdepth 3 -name "shared" -o -name "commonMain"
# Architectural patterns
find . -name "*ViewModel*.kt" -o -name "*Repository*.kt" -o -name "*UseCase*.kt" | head -n 5
# DI modules / components
find . -name "*Module*.kt" -o -name "*Component*.kt" | xargs grep -lE "module|inject|provides"
Phase C — Announce What You Found
After scanning, state your findings to the user before writing any code:
"I've detected this is a KMP project using Compose UI and Koin for DI. I will follow these patterns for the new feature."
Then wait for confirmation before proceeding.
2. Library Detection Matrix
| Category | Check For | Implementation Strategy |
|---|---|---|
| DI | hilt-android, koin-android, dagger |
Use @HiltViewModel, by inject(), or @Inject — match what is already in the codebase |
| UI | androidx.compose, material |
Prioritize Compose. Use XML/ViewBinding only if Compose is absent |
| Async | kotlinx-coroutines, rxjava |
Use Flow/suspend for Coroutines; Observable/Single for RxJava |
| Network | ktor-client, retrofit2, okhttp |
Use HttpClient for Ktor; interface + annotations for Retrofit |
| Persistence | room, realm, sqldelight, datastore |
Use @Database/@Entity for Room; Realm.write for Realm; Database for SQLDelight |
| Image Loading | coil, glide |
Use AsyncImage for Coil; GlideImage / Glide.with for Glide |
| Testing | mockk, mockito |
Use mockk<> / every for MockK; mock() / verify for Mockito |
| KMP | commonMain, expect/actual |
Place core business logic and network layers in commonMain |
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 · 172 lines · 0 tokens per session scan A 686bf0dda1ae
android-agent-guidelines is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,535 tokens. 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 agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
rn-builder
Expo + React Native (TypeScript) implementation specialist. Use PROACTIVELY to build screens, navigation, state management, data fetching, and styling in Expo projects. Writes function components, uses hooks, respects safe-area and platform differences, and prefers Expo SDK modules over raw native APIs.
mobile-specialist
モバイルUI・プラットフォームガイドラインの専門家。 iOS HIG / Material Design準拠、レスポンシブ対応、プラットフォーム固有パターンを評価する。 ui-review チームの一員として起動される。.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.