google-play-cli-skills AGENTS.md

google-play-cli-skills AGENTS.md is an instructions file for Codex, OpenCode from PollyGlot/google-play-cli-skills. It costs 445 tokens per session, scanned A, original, MIT.

Repository instructions for google-play-cli-skills, a collection of agent skills that use gplay, a command-line tool for the Google Play Developer API. The instructions explain how skills are organized and checked before publishing.

In plain words
What is it for?
Use them when adding or editing skills in this repository, especially to follow its file layout, writing rules, validation command, and publishing workflow.
Why use it?
They reduce the risk of documenting commands or options that the installed CLI does not support. A validation script checks each documented invocation against the actual gplay binary and CI repeats the check.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

Install

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.

agentmods
npx agentmods add instructions/pollyglot/google-play-cli-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/PollyGlot/google-play-cli-skills

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for google-play-cli-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pollyglot/google-play-cli-skills/agents-md.svg)](https://agentmods.dev/instructions/pollyglot/google-play-cli-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pollyglot/google-play-cli-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/pollyglot/google-play-cli-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 445 This file is loaded in full into every session.
When invoked 445 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00445 $0.00445
Opus 5 $0.00222 $0.00222
Sonnet 5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured today against content hash 718659c2f528, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

google-play-cli-skills AGENTS.md 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 today.

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.

AGENTS.md · 27 lines

What it actually says

CLAUDE.md

Agent skills pour le CLI gplay (Google Play Developer API) — un SKILL.md par skill sous skills/<nom>/, distribués via skills.sh.

  • Les skills pilotent gplay, le CLI est la source de vérité. Avant de pousser, lance python3 scripts/check-skills.py : il résout chaque invocation documentée contre le binaire installé et échoue sur un flag ou une commande qui n'existe pas. La CI le rejoue sur chaque PR et tous les lundis, pour attraper la dérive causée par une release de gplay. Il échoue aussi sur toute commande du binaire qu'aucune skill ne nomme : après une release de gplay, brew upgrade gplay puis relance-le avant d'analyser.
  • Merge : main exige le check CI check vert et un historique linéaire, pas de revue humaine. Une PR verte se merge avec gh pr merge <n> --squash --delete-branch, sans --admin. Un lundi rouge ouvre une issue skills-drift avec la sortie du script : c'est le ticket de la PR de rattrapage.
  • Ajouter ou renommer une skill change le pack que gplay install-skills épingle (commands/installskills/skills-pin.json dans le repo du CLI, commit
    • liste exacte). Après le merge ici, ouvre la PR jumelle de repin là-bas, typée fix pour qu'une release la livre.
  • Rédaction en anglais, instructions actionnables pour un agent, suivre le skill global writing-for-agents.
  • Pas de tiret cadratin dans la prose des skills, la barrière le refuse. Les blocs de code en sont exemptés : ils citent ce que le binaire imprime.
Changes

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.

  1. today Changed · +11 lines · +207 tokens per session 718659c2f528
  2. 5d ago First seen · 16 lines · 238 tokens per session scan A 104265213f1f

Subscribe to this mod's changes

google-play-cli-skills AGENTS.md is an instructions file published in the GitHub repository PollyGlot/google-play-cli-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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.