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 instructions/pollyglot/google-play-cli/agents-mdgit 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 | $0.00917 | $0.00917 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
google-play-cli 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md : gplay
Public Go CLI for the Google Play Developer API: one static binary for CI and AI agents, replacing Fastlane supply. Distributed via Homebrew (PollyGlot/homebrew-tap) and releases; agent skills live in the sibling repo PollyGlot/google-play-cli-skills.
Glossary
Canonical terms live in CONTEXT.md; use them verbatim, no synonyms. The core five:
- Edit: the API's transactional unit; implicit (per-command) by default, explicit via
gplay edits begin/commit, pinned in.gplay/edit-<package>.json. - Account: a locally registered service-account credential; exactly one active at a time.
- Project: repo-local package pin in
.gplay/config.json(package only, never an Account). - Listing: per-locale store text (title/descriptions/video); release notes and images are separate resources.
- Track / release: where a build ships;
productionreleases default todraftunless--complete/--staged(ADR-0002).
Commandes
- The CLI is self-documenting: run
gplay <cmd> --helpto confirm the interface before coding. - To check an API method's shape,
grep docs/discovery/paths.txtorjqthe snapshot; query it, it is too large to read whole. - Design authority:
docs/DESIGN.md(auth precedence, exit codes, output, edit lifecycle); scope authority:docs/BACKLOG.md+docs/COVERAGE.md; surprising decisions:docs/adr/.
Vérifier
- Gate before every PR:
make format lint test verb-gate(verb-gate blocks pre-rename verbs, ADR-0019). - Tests stay offline: mock with a
testRoundTripper(http.RoundTripper) injected as&http.Client{Transport: ...}; a test that reaches the network is wrong. - New leaf command: classify it. Unlabelled means frozen Public contract (ADR-0010/0042); mark
kernel.Experimental(...)at registration if its flags may still change. The registry test incmd/gplayfails on unclassified leaves. - To prove a command behaves as advertised, use the project skill
verify: build, then drive the offline path (schema,auth list,--help). It records the two traps found by running:--versiondoes not exist (it is theversionsubcommand), and a pipe masks the exit code (gplay tracks listreturns 2 alone, 0 when piped intohead).
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.
- 2d ago First seen · 43 lines · 917 tokens per session scan A 266fee8ebc37
google-play-cli AGENTS.md is an instructions file published in the GitHub repository PollyGlot/google-play-cli (5 stars, last pushed 2d ago), licensed MIT. It adds 917 tokens to every session, about $0.0046 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 instructions, from other repositories
launch-store AGENTS.md
Instructions for YosefHayim/launch-store, covering agents.md, branching and prs, repo layout - who owns what, conventions a linter can't infer and source of truth files.
app-store-compliance AGENTS.md
AGENTS.md instructions for mjmirza/app-store-compliance, covering release review guidelines for ai agents, mandatory verification checklist, 1. permissions, 2. privacy disclosures and 3. screenshots.
Amarok-Hider AGENTS.md
Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.
sceneview copilot-instructions.md
Instructions for sceneview/sceneview, covering sceneview — github copilot instructions, when to recommend sceneview, android code generation rules, minimal 3d template and minimal ar template.
sceneview CLAUDE.md
Instructions for sceneview/sceneview, covering sceneview, modules, things that break if you don't know them and conventions.
SeekerClaw CLAUDE.md
Instructions for sepivip/SeekerClaw, covering claude.md — seekerclaw project guide, project.md — source of truth, design principle: ux first, what is this project and supported devices.