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 davideagostini/ai-dev-skills --skill android-compose-reviewgit clone --depth 1 https://github.com/davideagostini/ai-dev-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/davideagostini/ai-dev-skills/android-compose-review)<a href="https://agentmods.dev/skills/davideagostini/ai-dev-skills/android-compose-review"><img src="https://agentmods.dev/badge/skills/davideagostini/ai-dev-skills/android-compose-review/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.
<a href="https://agentmods.dev/skills/davideagostini/ai-dev-skills/android-compose-review"><img src="https://agentmods.dev/badge/skills/davideagostini/ai-dev-skills/android-compose-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00996 |
| Opus 5 | $0.00023 | $0.00498 |
| Sonnet 5 | $0.00009 | $0.00199 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
android-compose-review 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Android + Jetpack Compose reviewer focused on existing codebases.
Your job is to inspect $ARGUMENTS, identify the highest-signal Compose and architecture issues, and recommend or apply incremental improvements without forcing a greenfield rewrite. Follow the workflow below in order. Consult the relevant reference files before reviewing or changing direction.
Respect local project constraints. Improve the code incrementally, not ideologically.
MODES
Choose the mode from the user's wording:
review-only: audit, review, inspect, assesssafe-fixes: clean up, simplify, modernize, improvefix-and-validate: same assafe-fixes, plus run the smallest relevant validation
Default rules:
- Use
review-onlyfor review or audit requests - Use
safe-fixesfor cleanup, modernization, or incremental refactor requests - Use
fix-and-validateif the user explicitly asks to verify after edits
WORKFLOW
Step 1 — Determine the scope and baseline
→ Consult review-scope.md
- Identify the smallest correct scope: file, screen, module, or diff
- Prefer the user’s explicit paths or current git changes
- Check the local architecture and patterns before calling something a problem
- Decide whether the task is review-only or safe incremental cleanup
Step 2 — Review architecture and state ownership
→ Consult architecture.md → Consult principles.md
- Look for state ownership problems, business logic leaking into composables, and weak feature boundaries
- Check whether the current code follows local patterns or is drifting into ad hoc structure
- Prefer incremental improvements over broad rewrites
Step 3 — Review the relevant Compose concern
→ Consult the matching reference file for the touched area
Use:
- state-management.md for state and recomposition issues
- side-effects.md for lifecycle, effects, coroutines, and listeners
- view-composition.md for composable structure and slot patterns
- composition-locals.md for implicit data and ambient dependencies
- lists-and-scrolling.md for lazy lists, keys, grids, and paging
- performance.md for recomposition, allocations, and hot paths
- modifiers.md for modifier ordering and custom behavior
- accessibility.md for semantics and touch targets
What ships with it
16 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.
- README.md 4.0 KB
- references/accessibility.md 11 KB
- references/architecture.md 12 KB
- references/common-bugs.md 1.0 KB
- references/composition-locals.md 11 KB
- references/deprecated-migrations.md 19 KB
- references/lists-and-scrolling.md 13 KB
- references/modernization-checklist.md 1.3 KB
- references/modifiers.md 10 KB
- references/performance.md 10 KB
- references/principles.md 1.6 KB
- references/review-scope.md 952 B
- references/side-effects.md 13 KB
- references/state-management.md 11 KB
- references/validation.md 646 B
- references/view-composition.md 13 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.
- 9d ago First seen · 107 lines · 47 tokens per session scan A e03bcb69950a
android-compose-review is a skill published in the GitHub repository davideagostini/ai-dev-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 996 once invoked, about $0.0002 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
app-store-compliance
Run an enterprise pre submission compliance audit on a mobile app project before uploading to the Apple App Store or Google Play. Use when the user is about to submit, ship, or release an iOS or Android app, when an app was rejected and needs a fix plan, when reviewing App Store Review Guidelines or Google Play policy…
cmp-audit
Adversarial audit of one subsystem of a Kotlin/Compose Multiplatform app against its spec AND against platform semantics — the class of defect desktop-tier tests cannot see (alarms, notifications, PendingIntents, reboot, process death, DST). Use this when the user says "audit the notifications", "double check X for…
compose-validate
Scan a Kotlin / Compose / Android codebase for anti-patterns: findViewById, GlobalScope, LiveData, Material 2 imports, lowercase composables, LazyColumn without key, kapt, kotlinCompilerExtensionVersion, force-unwrap !!, Log.d, string nav routes, hardcoded dependency versions.
mobile-design
Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.
mobile-games
Mobile game development principles. Touch input, battery, performance, app stores.
flutter-dart-code-review
Library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.