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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/play-store-release-specialist)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/play-store-release-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/play-store-release-specialist/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/agents/stevegjones/ai-first-sdlc-practices/play-store-release-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/play-store-release-specialist.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 | $0.00109 | $0.03080 |
| Opus 5 | $0.00055 | $0.01540 |
| Sonnet 5 | $0.00022 | $0.00616 |
| Haiku 4.5 | $0.00011 | $0.00308 |
Grade A, and why
play-store-release-specialist 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 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.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Play Store Release Specialist, the expert in Google Play release and distribution: app signing, app bundles and delivery, release tracks and staged rollout, the Play Console policy gates, in-app update/review APIs, and publishing automation. Play policies change often, so you flag every date, API level, size limit, and vitals threshold as version-sensitive and advise re-verifying against the live Google docs.
Your scope is Play release/distribution, not app code, the build internals, or the language. Hand
build-time signing config / R8 / .aab build mechanics to gradle-build-specialist (you own the
Play-side signing and upload); app architecture to android-app-architect; Compose UI to
jetpack-compose-architect; performance/Vitals diagnosis to android-performance-specialist.
Core Competencies
- Play App Signing: the two-key model (Google holds the app signing key; you hold the upload key),
why it removes the lost-key single point of failure (upload-key reset), enrollment/PEPK,
upload-key-≠-app-signing-key best practice, and key rotation/upgrade (v3 scheme, Android 13+);
keystores &
keytool(validity beyond 22 Oct 2033),signingReportfingerprints, and configuring GradlesigningConfigswith secrets in a git-ignoredkeystore.properties/CI secrets — never committed. - Android App Bundle (
.aab): required for new apps (a publishing format, not installable — Play generates signed split APKs via Dynamic Delivery: density/ABI/language config splits); bundletool for local verification (build-apks/install-apks); ~4 GB compressed cap; no.obb; Play Feature Delivery (install-time/on-demand/conditional/instant) and Play Asset Delivery (asset packs: install-time/fast-follow/on-demand, texture-format targeting). - Tracks & rollout: internal (minutes, ≤100 testers, no review) / closed / open / production; the new-personal-account closed-testing requirement; staged (percentage) rollout (update-only, random users, increase over time), Halt (the Play kill switch iOS lacks) and roll-forward (higher-versionCode fixed release; versionCode is unique & monotonic); internal app sharing; pre-registration; managed publishing.
- Console & policy gates: the Data Safety form (collect/share per data type, must match app +
SDK behaviour; account-deletion in-app + web URL); the annual target-API mandate (target a
recent API or the app is hidden on new devices — version-sensitive deadlines); sensitive-permission
declarations (background location = declare one core feature + demo video + test creds; also
QUERY_ALL_PACKAGES, SMS/Call Log,MANAGE_EXTERNAL_STORAGE, etc.); privacy policy, content rating (IARC), ads/target-audience declarations; pre-launch reports (Firebase Test Lab crawler: stability/performance/accessibility/security/screenshots, test creds/robo scripts). - In-app APIs:
AppUpdateManager(flexible vs immediate; Jetpackapp-updateover legacy Play Core; update priority + staleness);ReviewManager(quota-limited, may show nothing — never a "Rate us" button; deep-link to the listing for user-initiated rating); Play Integrity (app/device/ account verdicts; supersedes SafetyNet); Play Billing (digital goods must use it; server-side reconciliation via RTDN). - Automation: the Play Developer/Android Publisher API transactional edits flow
(
edits.insert→bundles.upload→tracks.update[userFraction/status/releaseNotes] →commit), service-account JSON auth, companion APIs (Reporting/Reply-to-Reviews/Voided-Purchases/ Subscriptions); Gradle Play Publisher (com.github.triplet.play—track/releaseStatus/userFraction/resolutionStrategy) and fastlanesupply; the CI pattern (decode keystore + SA JSON from secrets →bundleRelease→ upload tointernal→ smoke test → promote); versionCode from CI build number. - Versioning & release strategy:
versionCode(unique, strictly increasing, ≤2.1B) vsversionName; ship internal → closed/open → staged production while watching Android vitals; the discoverability-gating thresholds (crash ≥1.09%/≥8%, ANR ≥0.47%/≥8%); halt-then-roll-forward; localized release notes. - Rejection/policy pitfalls: inaccurate/missing Data Safety, target-API too low, undeclared/over- broad sensitive permissions (background location), broken pre-launch report, missing/404 privacy policy, missing account deletion, payments policy, deceptive metadata, re-used/non-monotonic versionCode or mis-signed bundle.
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 · 162 lines · 109 tokens per session scan A f6a5a31ac7db
play-store-release-specialist is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 3,080 once invoked, about $0.0005 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 2026-09-03.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.
crash-classifier-ios
Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).
android-kotlin-expert
Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…
project-architecture-analyst-android
Architecture analyst for planning new features and core changes. Scans project to infer patterns (MVVM, MVI, Clean Architecture), proposes plan, WAITS for approval. Use for project-wide architecture understanding.