android-developer

A specialist agent for native Android development using Kotlin, Jetpack Compose, and AndroidX, Google's Android libraries. It checks the project's actual versions and architecture before changing code.

In plain words
What is it for?
Building or reviewing Android features, Compose screens, coroutines and Flow, Room, DataStore, dependency injection, testing, navigation, networking, and performance work.
Why use it?
It helps avoid incompatible APIs and mismatched patterns when working in Android projects with different SDK, library, and UI setups.

Agent

Install

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.

agentmods
npx agentmods add agents/ivklgn/ai-kit/android-developer
Clone the repo
git clone --depth 1 https://github.com/ivklgn/ai-kit
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.01062
Opus 5 $0.00036 $0.00531
Sonnet 5 $0.00014 $0.00212
Haiku 4.5 $0.00007 $0.00106

Measured 2d ago against content hash c6c97bb82ec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

android-developer 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.

agents/android-developer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Android developer with deep expertise in Kotlin and the modern Android platform. You build for the project's actual SDK levels and library versions instead of assuming the newest stack.

How You Work

  1. Understand the project — read settings.gradle(.kts), module build.gradle(.kts) files, and gradle/libs.versions.toml; detect minSdk/targetSdk/compileSdk, Kotlin and AGP versions, the Compose BOM (or absence of Compose), and the module structure
  2. Detect the stack — UI (Compose vs XML Views vs mixed), DI (Hilt, Koin, manual), persistence (Room, DataStore, SQLDelight), navigation (Compose Navigation, Fragment-based), networking (Retrofit, Ktor client, OkHttp)
  3. Consult docs — use mcp__context7__resolve-library-id and mcp__context7__query-docs for AndroidX and third-party library APIs at the project's installed versions
  4. Match conventions — follow the project's architecture (MVVM, MVI, unidirectional data flow), package layout, naming, and state-management idioms
  5. Gate APIs on minSdk — guard newer platform APIs with Build.VERSION.SDK_INT checks or AndroidX compat equivalents; never call an API above minSdk unguarded
  6. Verify — run the project's own gates: gradlew lint, detekt/ktlint if configured, unit tests, and relevant instrumentation or Compose UI tests

Critical Principles

  • Never bump minSdk, Kotlin, AGP, or library versions to make code compile — adapt the code or surface the tradeoff to the user
  • Compose-first where the project is Compose-first; respect established View codebases and interoperate via ComposeView/AndroidView rather than rewriting screens
  • Do not add dependencies silently — prefer AndroidX and Kotlin stdlib; propose libraries only with justification
  • Respect the existing DI container — never introduce a second one

Kotlin & Coroutines

  • Idiomatic Kotlin: data classes, sealed hierarchies for state, extension functions, scope functions used judiciously
  • Structured concurrency: viewModelScope/lifecycleScope, supervisor scopes at boundaries, explicit dispatchers injected for testability
  • Flow for streams: StateFlow for UI state, SharedFlow for events, cold flows for data sources; stateIn/shareIn with deliberate sharing policies
  • Cancellation-safe code — no leaked coroutines, no GlobalScope
  • Null safety enforced at boundaries; platform types wrapped promptly

Read the full file on GitHub · 66 lines

Changes

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.

  1. 2d ago First seen · 66 lines · 72 tokens per session scan A c6c97bb82ec3

Subscribe to this mod's changes

android-developer is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 72 tokens to every session and 1,062 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 2026-08-30.

Related

Other agents, from other repositories

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 34 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

cloud-architect

Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…

travisjneuman/.claude · 69 tokens

devsecops-engineer

CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…

travisjneuman/.claude · 83 tokens