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/skydoves/android-testing-skills/validating-compose-stabilitynpx skills add skydoves/android-testing-skills --skill validating-compose-stabilitygit clone --depth 1 https://github.com/skydoves/android-testing-skillsWhat 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 | $0.00229 | $0.03279 |
| Opus 5 | $0.00114 | $0.01639 |
| Sonnet 5 | $0.00046 | $0.00656 |
| Haiku 4.5 | $0.00023 | $0.00328 |
Grade A, and why
validating-compose-stability 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validating Compose Stability — A CI Gate On Skippability And Parameter Stability
Compose stability — whether a composable is skippable/restartable and whether its parameters are stable — is invisible until a recomposition profiler catches it in production. This skill makes it a build gate: snapshot the current stability of every composable into a committed .stability baseline, and fail CI when a change makes anything less stable. The tool is the Compose Stability Analyzer Gradle plugin. (Authoring composables for stability — @Immutable/@Stable, the compiler config file, deferred reads — is covered in the compose-performance-skills repo; this skill is purely the validation/CI layer.)
When to use this skill
- The user wants
./gradlew stabilityCheckto fail CI when a composable becomes unskippable or a parameter flips stable → unstable. - The user wants a committed, reviewable baseline of every composable's stability (
.stabilityfiles) so changes show up in PR diffs. - A recomposition regression shipped because nothing flagged a
Listparameter or a non-@Immutabledata class added to a hot composable. - The user mentions
stabilityDump,stabilityCheck,composeStabilityAnalyzer,@IgnoreStabilityReport, or "stability baseline". - The user wants warning-only locally and hard-fail in CI.
When NOT to use this skill
- The user wants to fix an unstable parameter (
@Immutable/@Stable,kotlinx.collections.immutable,stability_config.conffor external types, deferred state reads,derivedStateOf) — that is Compose performance authoring; see thecompose-performance-skillsrepo's stability skills. This skill only validates and gates. - The user wants to find which recompositions are firing at runtime (Layout Inspector recomposition counts,
Recomposermetrics, composition tracing) — different tool, runtime not build time. - The user is doing UI behavioral or screenshot testing — see
../../setup/choosing-test-rule-vs-runtest/SKILL.mdand../../preview/capturing-preview-screenshots-in-ci/SKILL.md.
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 · 218 lines · 229 tokens per session scan A 6539270a5df7
validating-compose-stability is a skill published in the GitHub repository skydoves/android-testing-skills (313 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 229 tokens to every session and 3,279 once invoked, about $0.0011 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.