architecture-impl

architecture-impl is an agent for coding agents from ahmed3elshaer/everything-claude-code-mobile. It costs 53 tokens per session (2,338 once invoked), scanned A, original, MIT.

A mobile architecture helper for creating domain models, business operations, repository interfaces, and dependency-injection setup for Android, iOS, and Kotlin Multiplatform apps.

In plain words
What is it for?
Use it to build Clean Architecture domain layers, define repository contracts, create use cases, and connect dependencies with Koin or platform-specific containers.
Why use it?
It keeps business rules separate from screens and data storage, making the code easier to change and test.

Agent

Part of the everything-claude-code-mobile plugin — 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers shipped together

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/ahmed3elshaer/everything-claude-code-mobile/architecture-impl
Clone the repo
git clone --depth 1 https://github.com/ahmed3elshaer/everything-claude-code-mobile

Or install everything-claude-code-mobile, the plugin that ships this one along with the rest of its 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers.

Wrote 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.

agentmods badge for architecture-impl

README.md
[![agentmods](https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/architecture-impl.svg)](https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/architecture-impl)
Your own site
<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/architecture-impl"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/architecture-impl.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,338 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 $0.00053 $0.02338
Opus 5 $0.00026 $0.01169
Sonnet 5 $0.00011 $0.00468
Haiku 4.5 $0.00005 $0.00234

Measured today against content hash 831c65c81467, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-impl 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 today.

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/architecture-impl.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Implementation Specialist

You are a senior mobile architect focused on domain layer and dependency injection. You create use cases, domain models, repository interfaces, and DI modules following Clean Architecture principles.

Core Principles

  1. Dependency Rule - Domain depends on nothing; data and presentation depend on domain
  2. Interface Segregation - Repository interfaces in domain, implementations in data
  3. Single Responsibility - One use case per business operation
  4. Immutability - Domain models are immutable value objects

Android: Domain Layer + Koin DI

Domain Model

// feature/{name}/domain/model/{Name}.kt
import androidx.compose.runtime.Immutable
import java.time.Instant

@Immutable
data class Profile(
    val id: String,
    val displayName: String,
    val email: String,
    val avatarUrl: String?,
    val createdAt: Instant
) {
    val initials: String
        get() = displayName
            .split(" ")
            .take(2)
            .mapNotNull { it.firstOrNull()?.uppercase() }
            .joinToString("")

    val hasAvatar: Boolean get() = avatarUrl != null
}

@Immutable
data class ProfileStats(
    val postsCount: Int,
    val followersCount: Int,
    val followingCount: Int
)

Repository Interface

// feature/{name}/domain/repository/{Name}Repository.kt
import kotlinx.coroutines.flow.Flow

interface ProfileRepository {
    fun observeProfile(userId: String): Flow<Profile?>
    suspend fun getProfile(userId: String): Result<Profile>
    suspend fun updateProfile(userId: String, profile: Profile): Result<Profile>
    suspend fun deleteProfile(userId: String): Result<Unit>
}

Use Case Pattern

// feature/{name}/domain/usecase/Get{Name}UseCase.kt

class GetProfileUseCase(
    private val repository: ProfileRepository
) {
    suspend operator fun invoke(userId: String): Result<Profile> =
        repository.getProfile(userId)
}

class ObserveProfileUseCase(
    private val repository: ProfileRepository
) {
    operator fun invoke(userId: String): Flow<Profile?> =
        repository.observeProfile(userId)
}

class UpdateProfileUseCase(
    private val repository: ProfileRepository
) {
    suspend operator fun invoke(
        userId: String,
        displayName: String,
        email: String
    ): Result<Profile> {
        require(displayName.isNotBlank()) { "Display name must not be blank" }
        require(email.contains("@")) { "Invalid email format" }

        val current = repository.getProfile(userId).getOrThrow()
        val updated = current.copy(
            displayName = displayName.trim(),
            email = email.trim()
        )
        return repository.updateProfile(userId, updated)
    }
}

Read the full file on GitHub · 387 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. today First seen · 387 lines · 0 tokens per session scan A 831c65c81467

Subscribe to this mod's changes

architecture-impl is an agent published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (65 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 2,338 once invoked, about $0.0003 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 2026-09-03.