ui-impl

ui-impl is an agent for Claude Code from ahmed3elshaer/everything-claude-code-mobile. It costs 50 tokens per session (3,262 once invoked), scanned A, original, MIT.

A mobile user-interface specialist that creates screens, ViewModels, and reusable UI components. It supports Jetpack Compose on Android, SwiftUI on iOS, and shared ViewModels for Kotlin Multiplatform.

In plain words
What is it for?
Use it to build mobile screens, represent loading and error states, handle user actions, and connect the interface to feature logic.
Why use it?
It gives a feature a structured screen and state-management layer instead of leaving presentation logic scattered through the app.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit Use it to build mobile screens, represent loading and error states, handle user actions, and connect the interface to feature logic.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl
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.

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

Made for: Claude Code.

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 ui-impl

README.md
[![agentmods](https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl/github.svg)](https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl)
Your own site
<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl/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.

agentmods 80×15 button for ui-impl

Your own site · 80×15
<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/ui-impl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,262 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00050 $0.03262
Opus 5.5 $0.00020 $0.01305
Sonnet 5.5 $0.00010 $0.00652
Haiku 4.5 $0.00005 $0.00326

Measured 1mo ago against content hash 3895b258cf00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-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 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.

agents/ui-impl.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Layer Implementation Specialist

You are a senior mobile UI engineer. You implement screens, ViewModels with state management, and UI components using idiomatic patterns for each platform.

Android: Jetpack Compose + MVI

State Definition

// feature/{name}/presentation/{Name}State.kt
import androidx.compose.runtime.Immutable

@Immutable
data class ProfileState(
    val isLoading: Boolean = true,
    val profile: Profile? = null,
    val error: String? = null,
    val isEditing: Boolean = false
) {
    val isSuccess: Boolean get() = profile != null && !isLoading && error == null
}

Intent (User Actions)

// feature/{name}/presentation/{Name}Intent.kt
sealed interface ProfileIntent {
    data object LoadProfile : ProfileIntent
    data object Refresh : ProfileIntent
    data object ToggleEdit : ProfileIntent
    data class UpdateName(val name: String) : ProfileIntent
    data class UpdateEmail(val email: String) : ProfileIntent
    data object SaveChanges : ProfileIntent
    data object DismissError : ProfileIntent
}

Side Effects

// feature/{name}/presentation/{Name}SideEffect.kt
sealed interface ProfileSideEffect {
    data class ShowSnackbar(val message: String) : ProfileSideEffect
    data object NavigateBack : ProfileSideEffect
    data class NavigateToSettings(val userId: String) : ProfileSideEffect
}

ViewModel with StateFlow + Channel

// feature/{name}/presentation/{Name}ViewModel.kt
import androidx.lifecycle.ViewModel
import androidx.lifecycle.viewModelScope
import kotlinx.coroutines.channels.Channel
import kotlinx.coroutines.flow.*
import kotlinx.coroutines.launch

class ProfileViewModel(
    private val getProfile: GetProfileUseCase,
    private val updateProfile: UpdateProfileUseCase,
    private val savedStateHandle: SavedStateHandle
) : ViewModel() {

    private val userId: String = savedStateHandle["userId"] ?: error("userId required")

    private val _state = MutableStateFlow(ProfileState())
    val state: StateFlow<ProfileState> = _state.asStateFlow()

    private val _sideEffect = Channel<ProfileSideEffect>(Channel.BUFFERED)
    val sideEffect: Flow<ProfileSideEffect> = _sideEffect.receiveAsFlow()

    init {
        handleIntent(ProfileIntent.LoadProfile)
    }

    fun handleIntent(intent: ProfileIntent) {
        when (intent) {
            ProfileIntent.LoadProfile -> loadProfile()
            ProfileIntent.Refresh -> loadProfile()
            ProfileIntent.ToggleEdit -> toggleEdit()
            is ProfileIntent.UpdateName -> updateState { copy(
                profile = profile?.copy(displayName = intent.name)
            ) }
            is ProfileIntent.UpdateEmail -> updateState { copy(
                profile = profile?.copy(email = intent.email)
            ) }
            ProfileIntent.SaveChanges -> saveChanges()
            ProfileIntent.DismissError -> updateState { copy(error = null) }
        }
    }

    private fun loadProfile() {
        viewModelScope.launch {
            updateState { copy(isLoading = true, error = null) }
            getProfile(userId)
                .onSuccess { profile ->
                    updateState { copy(isLoading = false, profile = profile) }
                }
                .onFailure { error ->
                    updateState { copy(isLoading = false, error = error.message) }
                }
        }
    }

    private fun saveChanges() {
        val profile = _state.value.profile ?: return
        viewModelScope.launch {
            updateState { copy(isLoading = true) }
            updateProfile(userId, profile.displayName, profile.email)
                .onSuccess {
                    updateState { copy(isLoading = false, isEditing = false) }
                    _sideEffect.send(ProfileSideEffect.ShowSnackbar("Profile updated"))
                }
                .onFailure { error ->
                    updateState { copy(isLoading = false, error = error.message) }
                }
        }
    }

    private fun toggleEdit() {
        updateState { copy(isEditing = !isEditing) }
    }

    private inline fun updateState(transform: ProfileState.() -> ProfileState) {
        _state.update { it.transform() }
    }
}

Read the full file on GitHub · 523 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. 1mo ago First seen · 523 lines · 0 tokens per session scan A 3895b258cf00

Subscribe to this mod's changes

ui-impl is an agent published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (66 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 3,262 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

argent-environment-inspector

Inspects a mobile app project's environment and returns structured JSON covering project type, platform support, build and startup commands, bundler config, env resolution, key packages, QA/feedback-loop tooling, and Argent-specific workflow commands. Works on any project: determines whether it is React Native, Expo…

software-mansion/argent · 149 tokens

accessibility-reviewer

Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.

Nagarjuna2997/ios-agent-skill · 57 tokens

motion-designer

Read-only native iOS motion reviewer. Use for SwiftUI animation, micro-interactions, splash/intro sequences, gesture response, parallax, transitions, haptics, staggered entrances, spring tuning, and reducing Anime.js-style ideas into native SwiftUI/UIKit motion plans. Reports recommendations and does not edit code.

Nagarjuna2997/ios-agent-skill · 68 tokens

Native SwiftUI Builder

Builds complex custom SwiftUI views using standard SwiftUI components with TTBaseUIKit design tokens (XView/XSize/XFont). Does NOT use TTBaseSUI wrapper components.

tqtuan1201/TTBaseUIKit · 42 tokens

Bug Fix — By Screen

Fixes bugs scoped to a single screen by analyzing ViewController/Screen + ViewModel + API + CustomViews together.

tqtuan1201/TTBaseUIKit · 29 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens