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 skills add ashtanko/compose-android-template --skill using-chrisbanes-skillsgit clone --depth 1 https://github.com/ashtanko/compose-android-templateWrote 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/ashtanko/compose-android-template/using-chrisbanes-skills)<a href="https://agentmods.dev/skills/ashtanko/compose-android-template/using-chrisbanes-skills"><img src="https://agentmods.dev/badge/skills/ashtanko/compose-android-template/using-chrisbanes-skills.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 5.1 | $0.00054 | $0.01417 |
| Opus 5 | $0.00027 | $0.00709 |
| Sonnet 5 | $0.00011 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
using-chrisbanes-skills 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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using chrisbanes skills
Router only. Use this skill to choose the focused skill or skills for the task, then load those focused skills before giving detailed advice or editing code.
If a request already clearly matches a focused skill, use that skill directly. If several areas affect the work, load each relevant focused skill before acting on that area.
Common routes
| Task signal | Start with |
|---|---|
| Broad Compose screen review or refactor | compose-state-holder-ui-split, then add state, effects, layout, testing, or performance skills as needed |
Local Compose state, bare local var, remember { mutableStateOf(...) }, mutableStateListOf, or @ReadOnlyComposable |
compose-state-authoring |
| Deciding whether state belongs locally, hoisted, in a plain state holder, or in a screen state holder | compose-state-hoisting |
| ViewModel, component, controller, navigation, Flow collection, or dependency wiring mixed with UI layout | compose-state-holder-ui-split |
LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, navigation, snackbar, analytics, focus requests, or event Flow collection |
compose-side-effects |
| Recomposition, jank, compiler reports, Layout Inspector counts, unstable params, scroll reads, animation reads, or back-writing state across phases | compose-recomposition-performance |
Known Compose stability or skippability question, compiler classes.txt / composables.txt, collection parameters, or strong skipping |
compose-stability-diagnostics |
| Frame-rate state reads from scroll, animation, gestures, layout, or draw; value-form layout/draw modifiers; measurement state back-writing | compose-state-deferred-reads |
| Modifier parameters, root layout placement, hardcoded layout decisions, or modifier chain style | compose-modifier-and-layout-style |
| Reusable Compose component API with variable visual content, primitive content params, optional content params, or boolean shape flags | compose-slot-api-pattern |
| Compose visibility, value, color, size, transition, content swap, or choosing an animation API | compose-animations |
Keyboard, TV, desktop, D-pad, FocusRequester, focusProperties, key events, or initial focus behavior |
compose-focus-navigation |
| Compose UI tests, screenshot tests, previews, semantics, fake image loading, keyboard input, focus assertions, or interaction state tests | compose-ui-testing-patterns |
Coroutine scope ownership, init { launch }, non-suspending APIs that launch work, runBlocking, or cancellation handling |
kotlin-coroutines-structured-concurrency |
Kotlin branching, when expressions, guard conditions, sealed type exhaustiveness, smart casts, nullable branching, or complex if/else chains |
kotlin-control-flow |
StateFlow, SharedFlow, Channel, stateIn, SharingStarted, .value, one-shot events, sentinel initial values, or expensive update blocks |
kotlin-flow-state-event-modeling |
Kotlin Multiplatform platform APIs, source set boundaries, expect/actual, interfaces for platform services, permissions, files, sensors, native SDKs, or Compose Multiplatform interop |
kotlin-multiplatform-expect-actual |
| Kotlin function placement, member vs top-level function, extension functions, factories, primitive receivers, or extensions on String, collections, Flow, framework, or third-party types | kotlin-functions |
Single-field domain types, primitive obsession, or choosing @JvmInline value class vs data class |
kotlin-types-value-class |
| Polling or shepherding PRs/MRs, triaging review comments, fixing CI failures, or keeping reviews moving | shepherd |
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.
- 8d ago First seen · 45 lines · 54 tokens per session scan A 1d2f56afb3aa
using-chrisbanes-skills is a skill published in the GitHub repository ashtanko/compose-android-template (10 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 1,417 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 2026-08-31.
Other skills, from other repositories
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
migrating-to-modifier-node
Use this skill to author new custom Jetpack Compose modifiers and migrate legacy ones from Modifier.composed { } to Modifier.Node + ModifierNodeElement . Covers the persistent-node lifecycle (onAttach, onDetach, onReset, coroutineScope), the specialized node interfaces (DrawModifierNode, LayoutModifierNode…
configuring-lazy-prefetch
Use this skill to tune Jetpack Compose lazy-layout prefetch with LazyLayoutCacheWindow (Compose Foundation 1.9+, @ExperimentalFoundationApi) and pausable composition in prefetch (Compose Foundation 1.10+, default on). Covers configurable Dp-based ahead/behind cache windows plumbed through…
iterating-with-ai-and-mcp
Use this skill to drive Compose HotSwan from an AI agent (Claude Code, Cursor, any MCP client) so the agent can edit a Kotlin file, trigger a hot reload, capture a device screenshot, evaluate the result against a design intent, and iterate without a human in the loop. Covers the seven HotSwan MCP tools…