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 fortunto2/solo-factory --skill android-releasegit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote 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/fortunto2/solo-factory/android-release)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/android-release"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/android-release.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 | $0.00187 | $0.04788 |
| Opus 5 | $0.00093 | $0.02394 |
| Sonnet 5 | $0.00037 | $0.00958 |
| Haiku 4.5 | $0.00019 | $0.00479 |
Grade A, and why
solo-android-release scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`--remote-debugging-port` (check `curl -s localhost:9222/json/version` before promising anything). How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
android-release — ship Android to testers, then to Play
Start with MINIMAL (a working tester link in minutes). Do FULL only when the user wants the
public Play listing. Sibling skill: ios-release for iPhone/TestFlight.
Golden rules:
- Never hit final publish/"Send for review" without the user's OK — it's outward-facing. Filling drafts is fine; an internal-testing rollout is low-risk + reversible, so a prior "set it all up" covers it — but state what you did.
- Back up the keystore + password — losing it = can't update the same Play listing.
- Browser work: the user logs in (never touch their password/2FA); you drive the forms after.
Playwright MCP runs its own persistent Chromium profile, NOT the user's Chrome — a Chrome that
is "already logged in" is invisible to it, and you can't attach unless it was started with
--remote-debugging-port(checkcurl -s localhost:9222/json/versionbefore promising anything). So: open the Google sign-in page, hand the window over, wait. The login then sticks for later sessions. - The app may live in someone else's developer account (client/agency who granted you access).
play.google.com/console/developersshows a "Choose developer account" list — one Google login can hold several. Before concluding "the app isn't here", check every developer account in that list, not just the app list of the first one. Newly granted access appears there after a reload.
Which track? (who can use the link)
| Track | Who can install via link | Setup needed |
|---|---|---|
| Internal testing | only Google accounts on your list (≤100) | almost none — no review |
| Closed testing | accounts on a list or a Google Group | + content rating, data safety |
| Open testing | anyone with the link | + full store listing, content rating, target audience, data safety, review |
| GitHub APK (sideload) | literally anyone, no Google account | none — but "unknown sources" prompt |
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 · 281 lines · 187 tokens per session scan A 9dbb4377d5e5
solo-android-release is a skill published in the GitHub repository fortunto2/solo-factory (18 stars, last pushed today), licensed MIT. It adds 187 tokens to every session and 4,788 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
phone-harness
Control the user's phone — iPhone through the Mac's iPhone Mirroring window, or an Android over adb: open apps, tap, type, swipe, read the screen.
ui-mobile
Mobile UI patterns - React Native, iOS/Android, touch targets.
android-kotlin
Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing.
app-ui-design
Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.
mobile-development
Configure ServiceNow Mobile (Now Mobile/Agent) — syssgmobileapp screens, card builders, push notifications, offline sync rules, mobile actions for barcode/GPS, and offline-queue change processing.
apple-ecosystem-expert
Expert guide for Apple Ecosystem development. Covers iOS support, Safari WebKit compatibility, PWAs (Progressive Web Apps) for iOS, and Human Interface Guidelines (HIG) for web and native apps / Panduan ahli pengembangan ekosistem Apple (iOS & Web).