compose-inspector

compose-inspector is a skill for Claude Code, Codex from rabee-elkholy/android-harness-kit. It costs 39 tokens per session (462 once invoked), scanned A, original, MIT.

A review skill for Jetpack Compose, Android's toolkit for building user interfaces. It checks how UI updates, state, lists, layout direction, and themes are handled.

In plain words
What is it for?
Reviewing recomposition behavior, immutable or stable data, remembered calculations, lazy-list keys, state passing, right-to-left layouts, and theme usage.
Why use it?
It helps catch unnecessary UI work, unstable state, localization problems, and list or layout mistakes before they affect users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing recomposition behavior, immutable or stable data, remembered calculations, lazy-list keys, state passing, right-to-left layouts, and theme usage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rabee-elkholy/android-harness-kit/compose-inspector
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.

Any agent
npx skills add rabee-elkholy/android-harness-kit --skill compose-inspector
Clone the repo
git clone --depth 1 https://github.com/rabee-elkholy/android-harness-kit

Made for: Claude Code, Codex.

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 compose-inspector

README.md
[![agentmods](https://agentmods.dev/badge/skills/rabee-elkholy/android-harness-kit/compose-inspector/github.svg)](https://agentmods.dev/skills/rabee-elkholy/android-harness-kit/compose-inspector)
Your own site
<a href="https://agentmods.dev/skills/rabee-elkholy/android-harness-kit/compose-inspector"><img src="https://agentmods.dev/badge/skills/rabee-elkholy/android-harness-kit/compose-inspector/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 compose-inspector

Your own site · 80×15
<a href="https://agentmods.dev/skills/rabee-elkholy/android-harness-kit/compose-inspector"><img src="https://agentmods.dev/badge/skills/rabee-elkholy/android-harness-kit/compose-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 462 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 $0.00039 $0.00462
Opus 5.5 $0.00016 $0.00185
Sonnet 5.5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 1mo ago against content hash 8f7e1ef4a9c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compose-inspector 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/skills/compose-inspector/SKILL.md · 22 lines

What it actually says

Compose Inspector & Layout Verifier

1. Composition & Performance Safety Checks

  • Stability: Ensure UI state data classes containing Collections (List, Set, Map) are annotated with @Immutable or @Stable to prevent unnecessary recompositions.
  • Calculations: Verify remember is used for expensive object allocations or formatting inside composables.
  • Fast-Changing State: Use derivedStateOf when reading rapidly changing states (e.g., lazyListState.firstVisibleItemIndex, scroll offset, real-time pedometer counters) to avoid recomposing the parent scope on every tick.
  • Lazy Lists: Every LazyColumn / LazyRow must specify explicit key lambdas using unique, stable IDs (e.g., key = { it.id }).
  • State Hoisting: Pass only immutable State and lambda callbacks down to leaf composables. Never pass ViewModel instances into reusable child components.

2. Layout & Localization Verification

  • RTL / LTR: Strictly use directional modifiers: Modifier.padding(start = ..., end = ...) instead of left/right.
  • Theme & Design Tokens: All colors and text styles must consume this app's theme tokens — MaterialTheme.colorScheme / MaterialTheme.typography. colorResource(R.color…) is allowed when matching existing XML colors. Never use raw hex colors or hardcoded fonts.
  • String Resources: Extract all text to values/strings.xml and values-ar/strings.xml.
  • Previews: Every independent UI component and screen state (Loading, Empty, Success, Error) must have a @Preview function wrapped in this app's theme (or MaterialTheme), including Arabic RTL (locale = "ar" or CompositionLocalProvider(LocalLayoutDirection provides LayoutDirection.Rtl)) and English LTR (locale = "en" or LayoutDirection.Ltr).
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 · 22 lines · 39 tokens per session scan A 8f7e1ef4a9c5

Subscribe to this mod's changes

compose-inspector is a skill published in the GitHub repository rabee-elkholy/android-harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 462 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 2026-08-31.

Related

Other skills, from other repositories

adaptive-ui

Adaptive UI for Android — responsive layouts for phones, tablets, foldables, Chromebooks, and large screens. Use this skill for EVERY screen you build. Triggers on: WindowSizeClass, ListDetailPaneScaffold, SupportingPaneScaffold, ThreePaneScaffold, NavigationSuiteScaffold, NavigationRail, NavigationDrawer, adaptive…

piyushverma0/android-agent-skills · 157 tokens

design-system

Global-level design system for Android AI agents — Material 3 Expressive. Use this skill for visual consistency: spacing tokens, 8dp grid, M3 typography scale (15 styles), HCT color system, dynamic color Material You, shape system with morphing, motion tokens, physics-based spring animations, design tokens…

piyushverma0/android-agent-skills · 144 tokens

compose-ui

Jetpack Compose UI best practices for AI agents building Android apps. Use this skill whenever writing any Composable function, building screens, handling UI state, working with Scaffold, LazyColumn, ModalBottomSheet, BottomSheet, edge-to-edge, IME keyboard insets, recomposition, side effects, LaunchedEffect…

piyushverma0/android-agent-skills · 131 tokens

material3

Material 3 Expressive components and theming for Android AI agents. Use this skill for any M3 component: TopAppBar, LargeTopAppBar, CenterAlignedTopAppBar, BottomAppBar, FAB, ExtendedFAB, NavigationBar, NavigationRail, NavigationDrawer, NavigationSuiteScaffold, ModalBottomSheet, Chip (Filter/Assist/Input/Suggestion)…

piyushverma0/android-agent-skills · 172 tokens

design-tokens

Material 3 design system foundation for Android apps. Use this skill for ANY theming, color, spacing, shape, or elevation work — MaterialTheme, colorScheme, ColorScheme roles, lightColorScheme, darkColorScheme, dynamicColorScheme, primary/secondary/tertiary/surface/background tokens, onSurface, onBackground…

piyushverma0/android-agent-skills · 162 tokens

accessibility

Android accessibility for AI agents. Use this skill whenever implementing accessibility, TalkBack support, content descriptions, semantic properties, touch target sizes, contrast ratios, screen reader support, contentDescription, semantics modifier, clearAndSetSemantics, mergeDescendants, heading, stateDescription…

piyushverma0/android-agent-skills · 101 tokens