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 agentmods add agents/pollyglot/google-play-cli/skillsgit clone --depth 1 https://github.com/PollyGlot/google-play-cliWhat 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 | $0.00030 | $0.00674 |
| Opus 5 | $0.00015 | $0.00337 |
| Sonnet 5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
skills 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills drive gplay from natural-language prompts. Each skill is a
folder with a SKILL.md that documents the intent, the gplay commands it
runs, and the safety rails it enforces. They live in a companion repository:
PollyGlot/google-play-cli-skills.
Install
gplay install-skills
The skills are fetched with git from a commit pinned inside the gplay
binary, so two runs of the same version install the same reviewed files.
Nothing else is executed: no Node, no package runner, no script from the
skills repository. git is the only requirement.
They land in ~/.claude/skills, user-wide, which Claude Code and the agent
frameworks following that layout read. Use --dir to install elsewhere. Only
the skills listed below are replaced; anything else in that directory is left
alone, and a failed install is rolled back.
The roster
One skill per workflow, plus a foundation skill for the conventions they all share:
| Skill | Drives |
|---|---|
gplay-cli-usage |
Credential and package resolution, output, exit codes, safety gates, the Edit lifecycle (foundation) |
gplay-setup |
Auth onboarding: service account, login, doctor |
gplay-apps |
App registry, reachable apps, app details |
gplay-release-flow |
Upload, promote, staged rollouts, mappings, Internal App Sharing |
gplay-tracks |
Tracks, closed-track testers, country availability |
gplay-reviews |
Review triage, replies, the monthly CSV history |
gplay-metadata-sync |
Store listing text and images |
gplay-compliance |
Data Safety declarations |
gplay-team |
Users, grants, permission vocabulary |
gplay-monetization |
Subscriptions and one-time products as declarative files |
gplay-orders |
Order lookup and refunds |
gplay-vitals |
Crash/ANR rates, error reports, Play-detected anomalies |
gplay-games |
Achievements and leaderboards configuration |
gplay-recovery |
App recovery actions when a shipped build is broken |
gplay-device-tiers |
Device tier configs for tiered asset delivery |
gplay-customapps |
Private app creation for managed Google Play |
gplay-appstore |
Alternative app store: catalog, update feed, hosted-app review |
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.
- 3d ago First seen · 61 lines · 30 tokens per session scan A bdbe205c12e3
skills is an agent published in the GitHub repository PollyGlot/google-play-cli (5 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 674 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 agents, from other repositories
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
crdb-error-reviewer
Reviews CockroachDB code changes for error handling quality, silent failures, and inappropriate fallback behavior. Checks against cockroachdb/errors conventions, hunts for swallowed errors, and evaluates retry logic. Use when reviewing any code change that touches error paths.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
code-reviewer
Go code review specialist. Proactively reviews code for quality, DDD compliance, idioms, and security. Use immediately after writing or modifying code.
bug-reviewer
Diff-only logic-bug reviewer for Kotlin/Android. Flags compile errors, null-safety regressions, off-by-one errors, swapped arguments, broken control flow, race conditions, resource leaks, and behavior that contradicts the function name. Read-only; emits structured JSON.
architect
Expert software architect for planning features, designing APIs, and architectural decisions. Use when starting new features, planning refactors, or making complex multi-package changes.