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 skills/rcosteira79/android-skills/composenpx skills add rcosteira79/android-skills --skill composegit clone --depth 1 https://github.com/rcosteira79/android-skillsWrote 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.
[](https://agentmods.dev/skills/rcosteira79/android-skills/compose)<a href="https://agentmods.dev/skills/rcosteira79/android-skills/compose"><img src="https://agentmods.dev/badge/skills/rcosteira79/android-skills/compose.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00201 | $0.02381 |
| Opus 5 | $0.00101 | $0.01190 |
| Sonnet 5 | $0.00040 | $0.00476 |
| Haiku 4.5 | $0.00020 | $0.00238 |
Grade A, and why
compose 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Expert Skill
Non-opinionated, practical guidance for writing correct, performant Compose code —
across Android, Desktop, iOS, and Web. Covers Jetpack Compose and Compose Multiplatform.
Backed by analysis of actual source code from androidx/androidx and
JetBrains/compose-multiplatform-core.
Workflow
When helping with Compose code, follow this checklist:
1. Understand the request
- What Compose layer is involved? (Runtime, UI, Foundation, Material3, Navigation)
- Is this a state problem, layout problem, performance problem, or architecture question?
- Is this Android-only or Compose Multiplatform (CMP)?
2. Analyze the design (if visual reference provided)
- If the user shares a Figma frame, screenshot, or design spec, consult
references/design-to-compose.md - Decompose the design into a composable tree
- Transcribe, don't adapt — copy, casing, punctuation and number format come across exactly; resolve each value to the token that matches it exactly, and add a token the theme lacks rather than substituting the nearest (
references/design-to-compose.md) - Map design tokens to MaterialTheme, spacing to CompositionLocals
- Identify animation needs —
references/animation.md(contentKey, phase rule, M3 motion tokens),references/animation-recipes.md(shimmer/loading-crossfade + choreography), orreferences/animation-advanced.md(shared-element, predictive back,drawBehind-for-color)
3. Consult the right reference
Read the relevant reference file(s) from references/ before answering:
| Topic | Reference File |
|---|---|
State-hoisting boundary (UI-value-drives-business-logic), derivedStateOf-capture trap, cross-phase back-writing, durable-state-over-events, @ReadOnlyComposable |
references/state-management.md |
Slot / content-API authoring — receiver scopes (RowScope), optional (nullable) slots, XxxDefaults, slot-vs-boolean-flag |
references/view-composition.md |
| Screen/content split (private content composable), framework-state-stays-in-UI (not hoisted to the ViewModel) | references/screen-structure.md |
| Modifier-as-API-contract rules (no hardcoded placement on a reusable root, caller-modifier-first) + chain ordering | references/modifiers.md |
Effects (LaunchedEffect/DisposableEffect/SideEffect), lifecycle effects (LifecycleResumeEffect), effect anti-patterns |
references/side-effects.md |
compositionLocalOf vs staticCompositionLocalOf (recomposition scope), custom locals, no-mutable-State-in-a-local |
references/composition-locals.md |
LazyList perf traps — indexOf()-O(n²), no-new-objects-in-key, animateItem, ReportDrawnWhen, infinite-scroll trigger |
references/lists-scrolling.md |
Navigation 3 (NavDisplay, back-stack-as-state, compose-shape guardrails); type-safe @Serializable routes |
references/navigation.md |
AnimatedContent contentKey-on-shape, defer-reads-to-latest-phase (lambda modifiers), M3 motion/easing tokens |
references/animation.md |
| Animation recipes (shimmer/loading-crossfade), sequential/parallel/staggered choreography | references/animation-recipes.md |
Shared-element transitions (sharedBounds/sharedElement/skipToLookaheadSize), drawBehind-for-animated-color, predictive back |
references/animation-advanced.md |
Extending the theme beyond M3's three slots — custom design tokens via CompositionLocal |
references/theming-material3.md |
| Touch targets, spacing, canonical layouts, foldables, M3 compliance audit | android-skills:android-ux |
| Recomposition skipping, stability, baseline profiles, benchmarking | references/performance.md |
Traversal order (traversalIndex / isTraversalGroup), live-region mode (Polite vs Assertive) |
references/accessibility.md |
FocusRequester, focusable(), focusProperties, key events, D-pad, TV, keyboard, focus restoration |
references/focus-navigation.md |
| Removed/replaced APIs, migration paths from older Compose versions | references/deprecated-patterns.md |
Styles API (experimental): Style {}, MutableStyleState, Modifier.styleable() |
references/styles-experimental.md |
Transcribing a design — exact copy/casing/number format, exact-token-vs-near-neighbour, missing-token-added-not-substituted, export-over-render as source of truth; Figma dropShadow/innerShadow (1.9+, chain placement), spacing/elevation design-token CompositionLocal |
references/design-to-compose.md |
| Production crash patterns, defensive coding, state/performance rules | references/production-crash-playbook.md |
CMP gotchas (collectAsState-in-commonMain, commonMain @Preview package, Lottie→Kottie, compiler-stability-non-JVM) + Android-only→CMP migration |
references/multiplatform.md |
| Desktop (Window, Tray, MenuBar), iOS (UIKitView), Web (ComposeViewport) | references/platform-specifics.md |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/accessibility.md 1.9 KB
- references/animation-advanced.md 3.4 KB
- references/animation-recipes.md 2.3 KB
- references/animation.md 4.4 KB
- references/composition-locals.md 2.4 KB
- references/deprecated-patterns.md 4.0 KB
- references/design-to-compose.md 7.1 KB
- references/focus-navigation.md 13 KB
- references/lists-scrolling.md 3.6 KB
- references/modifiers.md 10 KB
- references/multiplatform.md 3.8 KB
- references/navigation.md 3.8 KB
- references/performance.md 26 KB
- references/platform-specifics.md 3.7 KB
- references/production-crash-playbook.md 20 KB
- references/screen-structure.md 3.0 KB
- references/side-effects.md 3.7 KB
- references/state-management.md 10 KB
- references/styles-experimental.md 15 KB
- references/theming-material3.md 1.7 KB
- references/view-composition.md 7.9 KB
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.
- 5d ago First seen · 161 lines · 201 tokens per session scan A b1e8f916adf9
compose is a skill published in the GitHub repository rcosteira79/android-skills (136 stars, last pushed 10d ago), licensed MIT. It adds 201 tokens to every session and 2,381 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.