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/agent-guidegit 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 | $0.00041 | $0.01158 |
| Opus 5 | $0.00020 | $0.00579 |
| Sonnet 5 | $0.00008 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
agent-guide 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gplay is designed to be driven by AI agents: coding assistants, CI bots, autonomous release managers. This page is the contract an agent can rely on.
Machine-stable output
- Piped output (and
CI=true) defaults to JSON, so an agent running gplay through a shell tool gets JSON without asking. - For commands that wrap a Play API call, JSON is the API's own response shape (pass-through): schemas are documented by Google, not invented by gplay.
- stdout carries data only; logs and warnings go to stderr. Parsing stdout never breaks on a log line.
--output markdownrenders tables and checklists ready to paste into a PR comment or chat reply.
Semantic exit codes
The exit code taxonomy makes failure handling
decidable without parsing prose: 40/50 are retry-safe, 2 means the
command was malformed, 10/11 mean credentials/permissions, 60 means
state conflict.
Exit 3 is the agent-resolvable refusal: the command was well-formed,
but a named safety acknowledgment (--confirm, --grant-admin) is
missing, and the error names it. An agent can surface the decision to a
human, or re-run with the flag if its policy allows.
Under --output json, a failure also writes a structured envelope to stdout
({"error":{"exitCode","message","reasons","requires"}}), so the failure is
parseable without scraping stderr, and requires names the missing flag at
failure time, not just in a dry-run. See
output formats.
The read-only authority boundary: GPLAY_READONLY
--confirm and --grant-admin are advisory: an agent that holds the
credential can pass them itself. GPLAY_READONLY is the boundary a harness
imposes regardless of what the model chooses. When it is truthy
(1/true/yes/on), every command that mutates Google Play state is
refused with exit 4, before credential resolution and any network
call, while read commands and --dry-run of mutating commands still run. So
an agent can observe and plan against a production credential, but cannot
publish unless the environment lets it.
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 · 112 lines · 41 tokens per session scan A 84806000555b
agent-guide is an agent published in the GitHub repository PollyGlot/google-play-cli (5 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,158 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
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. launch-store is single-context: one CONTEXT.md + docs/adr/ at the repo root.
issue-tracker
Issues and PRDs for launch-store live as GitHub issues on YosefHayim/launch-store. Use the gh CLI for all operations - it infers the repo from git remote -v automatically inside a clone.
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker. launch-store uses the canonical names as-is.
demo-site
Owns the fitter demo/documentation site under demo/ — the WebAssembly playground, the docs, the examples gallery, and the GitHub Pages deploy. Use for any work on demo/index.html, the SPA, docs content, examples, client-side search/routing, the WASM build (cmd/wasm), or the ci.yaml pages job. Trigger phrases: "demo…
any-coding-agent
Compact control guide for coding agents without a named integration — Cline, Windsurf, Devin, Aider, OpenHands, or anything else that can run a shell command or speak MCP. The named guides (codex.md, claude-code.md, cursor.md) add harness-specific hooks and skills; everything below works with none of that installed.
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…