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 PollyGlot/google-play-cli-skills --skill gplay-cli-usagegit clone --depth 1 https://github.com/PollyGlot/google-play-cli-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/pollyglot/google-play-cli-skills/gplay-cli-usage)<a href="https://agentmods.dev/skills/pollyglot/google-play-cli-skills/gplay-cli-usage"><img src="https://agentmods.dev/badge/skills/pollyglot/google-play-cli-skills/gplay-cli-usage/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/pollyglot/google-play-cli-skills/gplay-cli-usage"><img src="https://agentmods.dev/badge/skills/pollyglot/google-play-cli-skills/gplay-cli-usage.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 | $0.00082 | $0.02490 |
| Opus 5.5 | $0.00033 | $0.00996 |
| Sonnet 5.5 | $0.00016 | $0.00498 |
| Haiku 4.5 | $0.00008 | $0.00249 |
Grade A, and why
gplay-cli-usage 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 10d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gplay CLI conventions (foundation)
Conventions shared by every gplay command; the normative source is
docs/DESIGN.md
in the CLI repo. --help wins over this skill when they disagree:
gplay --help # the whole command tree
gplay <group> --help # a namespace (releases, tracks, team, …)
gplay <group> <command> --help # one command, with its real flags
gplay exit-codes # the semantic exit-code table + diagnostic codes
Stability: the [experimental] banner
gplay is GA. A command whose --help opens with [experimental] sits outside
the Public contract (pin an exact release in CI, the banner says so); every
other surface holds until a major bump, so CI can pin v1
(stability).
gplay schema: the offline API map
Where --help documents gplay's own surface, gplay schema <query>
introspects the Android Publisher API offline (no credential, no HTTP):
methods, REST paths, types, enums. [experimental]; flags in
gplay schema --help.
gplay schema edits.tracks.update # a method's request/response, one hop deep
gplay schema Track # a type's fields, types, enums
gplay schema --command "releases upload" # the API methods a gplay command calls
Which credential
Highest priority first: --service-account <path-or-inline-JSON>,
--account <name>, GPLAY_SERVICE_ACCOUNT (path or inline JSON), then the
active stored Account (gplay auth login). Setup and diagnosis of exits
10/11: gplay-setup.
Which app (--package + project pinning)
Most commands need a target package. Resolution (ADR-0004):
--package com.example.appon the command, else- the package pinned in
.gplay/config.jsonfor the current repo.
Pin once with gplay init (or gplay apps init) so day-to-day commands need
no --package. Managing the registry of packages is the gplay-apps skill.
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.
- 10d ago Changed · +1 lines 5d4cd7083500
- 24d ago Changed · +4 lines cc71b39a4b85
- 1mo ago Changed · -56 lines · -2 tokens per session 300ec5afa283
- 1mo ago Changed · +41 lines 0f0e98c4666a
- 1mo ago First seen · 207 lines · 84 tokens per session scan A faee9a655e2d
gplay-cli-usage is a skill published in the GitHub repository PollyGlot/google-play-cli-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 2,490 once invoked, about $0.0003 per session on Opus 5.5. 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
compose-ui-builder
Open and edit checked-in .uid designs, compare real renders against references, and implement them in application code. Author and edit a Compose UI design over MCP against a compose-preview serve deployment — create a screen or a Wear widget, insert and edit nodes, and export the Kotlin, PNG or SVG. Also use when no…
compose-preview
Render a Jetpack Compose or Compose Multiplatform @Preview to PNG in one call (MCP renderpreview, or the compose-preview CLI) and look at it. Use whenever someone asks to render, show, or see what a composable, @Preview or Compose component looks like (including library components such as Material 3 or Wear M3…
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
xml-to-compose
Convert Android XML layouts to Jetpack Compose. Use when asked to migrate XML layouts, convert views to composables, or help with Compose migration. Handles layouts, widgets, attributes, styles, and resource references.
mavericks-mvi
Use when creating or modifying Mavericks 3.x State, MavericksState, MavericksViewModel, AssistedViewModelFactory, hiltMavericksViewModelFactory, ViewModelModule binding, initial args, Compose mavericksViewModel, collectAsStateWithLifecycle, Fragment MavericksView subscriptions, Async execute, setState, withState…
tailscale-deploy-adb
Deploy Android debug build to a physical device over Tailscale + Wireless ADB. Use when user wants to install a fresh APK on their phone remotely (from gym, cafe, anywhere outside home Wi-Fi). Triggers: "tailscale deploy", "deploy adb", "install on phone", "deploy to phone", "deploy debug build", "push apk to device"…