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/hamen/compose_skill/compose-agentnpx skills add hamen/compose_skill --skill compose-agentgit clone --depth 1 https://github.com/hamen/compose_skillWhat 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 | $0.00089 | $0.03784 |
| Opus 5 | $0.00044 | $0.01892 |
| Sonnet 5 | $0.00018 | $0.00757 |
| Haiku 4.5 | $0.00009 | $0.00378 |
Grade A, and why
compose-agent 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 2d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Agent
Review, write, or modify Jetpack Compose code for correctness, modern API usage, and adherence to the official AndroidX guidelines. Report only genuine problems — do not nitpick or invent issues.
Target track (unless the repo says otherwise):
- Kotlin
2.0.20+with Compose Compiler1.5.4+(Strong Skipping Mode on by default). - Jetpack Compose BOM current, Material 3,
androidx.lifecyclewithcollectAsStateWithLifecycle(). - Navigation 3 (
androidx.navigation3) when the project can adopt it; otherwise Navigation 2.8+. - Coroutines + Flow as the async primitives. Do not reach for RxJava or blocking I/O.
If the repo pins older versions, match the repo — but call out what the modern path would look like in a one-line note.
Review Process
- Check for deprecated or soft-deprecated API using
references/api.md. - Validate state and data flow using
references/state.md. - Validate side-effect choice (
LaunchedEffect,DisposableEffect,produceState,snapshotFlow,rememberUpdatedState) usingreferences/effects.md. - Review composable performance — stability, lambda modifiers, lazy list keys, deferred reads, cross-phase back-writes — using
references/performance.md. - Review modifier usage — ordering, lambda-form,
Modifier.Nodeovercomposed { }— usingreferences/modifiers.md. - Review navigation using
references/navigation.md— start from its decision table (Nav3 vs Nav2 type-safe vs plain state) before touching call sites. - Review coroutines and lifecycle collection using
references/concurrency.md. - Review Flow operators and StateFlow / SharedFlow shape (
stateIn,shareIn,flatMapvariants,combine, error handling, backpressure,asStateFlow()) usingreferences/flows.md. - Review composable API shape (parameter order, slots, naming, defaults) using
references/component-api.md. - Review UI testing patterns using
references/testing.mdwhen tests, semantics, screenshots, previews, or fake UI dependencies are in scope. - Review focus and keyboard / D-pad navigation using
references/focus.mdwhen the UI uses focus APIs, keyboard input, TV, desktop, ChromeOS, or accessibility focus behavior. - Review Compose Multiplatform / KMP boundaries using
references/kmp.mdwhen common code,expect/actual, platform services, native views, or shared UI targets are in scope. - Review animation API choice and lifecycle — declarative vs imperative,
rememberedAnimatable, target-driven launches,springovertween, deferred animated reads,AnimatedContentkeys — usingreferences/animation.mdwhen anyanimate*,Animatable,Transition,AnimatedVisibility,AnimatedContent, or infinite-transition API is in scope. - Review Paging 3 in Compose —
collectAsLazyPagingItems(the paging differ — notcollectAsStateWithLifecycle, which does not apply toPagingData), stableitemKey,LoadStatebranches, user-drivenrefresh()/retry()— usingreferences/paging.mdwhenLazyPagingItems,PagingData, orcollectAsLazyPagingItemsis in scope. - Final Kotlin style pass using
references/kotlin.md.
What ships with it
18 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.
- .claude-plugin/plugin.json 834 B
- .cursor-plugin/plugin.json 834 B
- evals/evals.json 6.7 KB
- references/animation.md 19 KB
- references/api.md 14 KB
- references/component-api.md 13 KB
- references/concurrency.md 9.3 KB
- references/effects.md 13 KB
- references/flows.md 24 KB
- references/focus.md 4.4 KB
- references/kmp.md 4.9 KB
- references/kotlin.md 8.1 KB
- references/modifiers.md 7.7 KB
- references/navigation.md 13 KB
- references/paging.md 13 KB
- references/performance.md 17 KB
- references/state.md 12 KB
- references/testing.md 4.3 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.
- 2d ago First seen · 197 lines · 89 tokens per session scan A 7c815dc8f21e
compose-agent is a skill published in the GitHub repository hamen/compose_skill (367 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 3,784 once invoked, about $0.0004 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.