Borrowing it
Nothing to install: this file belongs to OrellBuehler/play-console-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OrellBuehler/play-console-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/OrellBuehler/play-console-mcpWrote 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/instructions/orellbuehler/play-console-mcp/claude-md)<a href="https://agentmods.dev/instructions/orellbuehler/play-console-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/orellbuehler/play-console-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01929 | $0.01929 |
| Opus 5 | $0.00964 | $0.00964 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
play-console-mcp CLAUDE.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 6d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A STDIO MCP server that exposes the official Google Play Developer API (androidpublisher v3)
and the Play Developer Reporting API (v1beta1) as tools for AI agents, centered on user
feedback (read and reply to Play Store reviews) and release management (tracks, promotion,
staged rollouts), plus Android vitals (crash/ANR rates, error issues and reports). Published to npm
as @orellbuehler/play-console-mcp and run via npx; the compiled dist/index.js is the bin
entry. See README.md for the tool catalog and env-var reference.
Note the Android Management API is a different, unrelated API for enterprise device management — it is not used here.
Commands
npm run build # tsc -p tsconfig.build.json -> dist/
npm test # vitest run (all tests)
npm run test:watch # vitest watch
npm run lint # eslint src
npm run typecheck # tsc --noEmit
npm run format # prettier --write .
npm run format:check # prettier --check . (what CI runs)
Run a single test file or pattern:
npx vitest run src/__tests__/releases.test.ts
npx vitest run -t "promote_release"
CI (.github/workflows/ci.yml) runs format:check, lint, typecheck, and test + build on
Node 20 and 22 — all must pass. Run them locally before committing.
Architecture
Request flow: index.ts reads config, builds the server via server.ts:createServer(client, reportingClient, packageName, allowDestructive), and connects it over stdio. Each tool calls one of
the two REST clients.
src/index.ts— entry point. Stdio transport only (single-account).src/config.ts— reads env at import time and exits the process if neitherGOOGLE_SERVICE_ACCOUNT_KEYnorGOOGLE_SERVICE_ACCOUNT_KEY_PATHis set. Exportsconfig(includingallowDestructivefromGOOGLE_PLAY_ALLOW_DESTRUCTIVE),client(androidpublisher) andreportingClient(Play Developer Reporting).src/play/auth.ts—createTokenProvider(auth): signs an RS256 service-account JWT withjoseand exchanges it athttps://oauth2.googleapis.com/tokenfor an OAuth access token, cached until expiry with a 60 s buffer. The JWT carries both scopes (androidpublisherandplaydeveloperreporting), so one provider serves both clients. The key JSON is loaded lazily on first use (inline or from a file path). Nogoogleapis/google-auth-librarydependency.src/play/client.ts—GooglePlayClient, a thinfetchwrapper. One class, two instances built fromPUBLISHER_BASE_URLandREPORTING_BASE_URL.get/post/put/patch/del;posttakes optional query params (needed for:commit?changesNotSentForReview) and tolerates empty response bodies.uploadposts raw bytes with an explicitContent-TypetoPUBLISHER_UPLOAD_BASE_URLwithuploadType=media— that host is a separate prefix (/upload/androidpublisher/v3), which is why it is its own method. Throws on non-2xx with the response body in the message.src/play/edits.ts— the Play edits workflow, which every release write goes through:readWithEdit(insert edit → read → always delete) andwithEdit(insert → mutate →:validate+ delete for a dry run, or:commit; delete the edit on failure).src/play/format.ts—ok/err(MCP content envelopes;okpasses strings through unquoted) andresolvePackage(per-toolpackage_nameoverridingGOOGLE_PLAY_PACKAGE_NAME, throwing a helpful error if neither is set).src/tools/*.ts— each exports aregister*Tools(server, client, packageName?)function thatserver.tscalls:reviews,releases,listings,artifacts,recovery(all on the publisher client),vitalsandapps(on the reporting client).listingsandrecoverytake a fourthallowDestructiveargument.src/tools/shared.ts— Zod shapes reused across tool modules:packageArg,writeShape(validate_only+changes_not_sent_for_review) andreleaseNotesSchema. Reuse these instead of redeclaring them.
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.
- 6d ago First seen · 119 lines · 1,929 tokens per session scan A 8d2c53bd1c0f
play-console-mcp CLAUDE.md is an instructions file published in the GitHub repository OrellBuehler/play-console-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 1,929 tokens to every session, about $0.0096 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
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).