Amethyst is an Android client for Nostr, a social network protocol that lets people control their own social activity and connections. People use it to read and publish Nostr content, follow accounts, and exchange encrypted direct messages from Android and other supported platforms. The catalogue add-ons support workflows for developing or operating the client.
Borrowing it
Nothing to install: this file belongs to vitorpamplona/amethyst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vitorpamplona/amethyst/main/.claude/skills/android-expert/SKILL.mdgit clone --depth 1 https://github.com/vitorpamplona/amethystWrote 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/vitorpamplona/amethyst/android-expert)<a href="https://agentmods.dev/skills/vitorpamplona/amethyst/android-expert"><img src="https://agentmods.dev/badge/skills/vitorpamplona/amethyst/android-expert/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/vitorpamplona/amethyst/android-expert"><img src="https://agentmods.dev/badge/skills/vitorpamplona/amethyst/android-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 305 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00000 | $0.01881 |
| Opus 5.5 | $0.00000 | $0.00752 |
| Sonnet 5.5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
android-expert 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android-expert
amethyst/ is shrinking to an Android shim: entry points, services, system integrations and
the actuals of shared ports. Screens, the nav host and the bar / rail / drawer are shared UI in
commonsUI (see compose-expert). A new screen goes there even when only Android shows it.
Source root: amethyst/src/main/java/com/vitorpamplona/amethyst/ (an Android app module, not
KMP: there is no androidMain here). Flavor code is in amethyst/src/play/ and
amethyst/src/fdroid/.
Entry points
Amethyst.kt: theApplication. BuildsAppModules(Amethyst.instance) in the main process only.ui/MainActivity.kt: the single main Activity (launchMode="singleInstance").onCreatecallsenableEdgeToEdge()and setsAmethystTheme { ... AmethystApp(Amethyst.instance.sessionManager, AndroidAppRoot) }. Everything from there down is shared UI.ui/AndroidAppRoot.kt:object AndroidAppRoot : AppRoot, Android's implementation of the shared shell port (commonsUI/.../commons/ui/app/AppRoot.kt). It registers the Android-only destinations (androidDestinationsinui/navigation/AppNavigation.kt) and runsNavigateIfIntentRequested.ui/platform/AndroidAppPlatform.kt(AppPlatform) andui/platform/AndroidAppServices.kt(AppServices, the interface is incommons/.../commons/service/AppServices.kt): the other two ports the shared UI calls.- Other activities have their own windows:
ui/call/CallActivity,ui/screen/loggedIn/nests/room/activity/NestActivity,service/playback/pip/PipVideoActivity, the signer / napplet consent activities, andHealthConnectRationaleActivity.
Two processes
The app runs in main and :napplet. Read references/two-processes.md before
touching Amethyst.kt, an Application callback, or anything under napplet/. The sandbox
activities and services (NappletHostActivity, NappletBrowserActivity, NappletHostService,
NappletBrowserService) live in the :nappletHost module and are declared with
android:process=":napplet". The broker side (napplet/NappletBrokerService.kt,
NappletLaunchRegistry, consent) stays in amethyst/.
What ships with it
2 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.
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 Changed eb17f4e517df
- 25d ago Changed · -781 lines · -156 tokens per session 6f3b139e7f65
- 29d ago Changed · -89 lines · +7 tokens per session d09baaa788d3
- 1mo ago Changed · +15 lines e1b205952e09
- 1mo ago Changed · +8 lines a3c51092eea1
- 2mo ago First seen · 977 lines · 149 tokens per session scan A 2728ae96e8bf
android-expert is a skill published in the GitHub repository vitorpamplona/amethyst (1,620 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,881 tokens. 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.
android-expert compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| android-expertvitorpamplona/amethyst | Skill | 1.6k | yesterday | MIT | A | 0 | Claude Code |
| sceneview-iossceneview/sceneview | Skill | 1.4k | yesterday | Apache-2.0 | A | 148 | Codex |
| sceneviewsceneview/sceneview | Skill | 1.4k | yesterday | Apache-2.0 | A | 156 | Codex |
| compose-animationschrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 64 | Claude Code |
| compose-focus-navigationchrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| kotlin-androidericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 78 | Claude Code, Codex |
| compose-multiplatformericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |