Borrowing it
Nothing to install: this file belongs to chrischall/app-store-connect-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/chrischall/app-store-connect-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/app-store-connect-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/chrischall/app-store-connect-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/app-store-connect-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/app-store-connect-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/chrischall/app-store-connect-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/app-store-connect-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01648 | $0.01648 |
| Opus 5.5 | $0.00659 | $0.00659 |
| Sonnet 5.5 | $0.00330 | $0.00330 |
| Haiku 4.5 | $0.00165 | $0.00165 |
Grade A, and why
app-store-connect-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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
app-store-connect-mcp
MCP server for App Store Connect — apps, builds, TestFlight, customer reviews, sales/finance reports, and team users.
Commands
npm run build # tsc + esbuild bundle
npm test # typecheck (src, then src + tests via tsconfig.test.json) + vitest run
npm run test:watch # vitest in watch mode
Architecture
src/
index.ts MCP server entry point — registers all tool modules, starts stdio transport
client.ts AppStoreConnectClient — ES256 JWT signing, Bearer auth, 401/429 retry
types.ts AscEnvelope/AscResource (JSON:API) and ToolResult types
tools/
apps.ts list/get apps, App Store versions, app infos
testflight.ts builds, beta groups/testers, invitations, beta review submission
reviews.ts customer reviews, developer responses
sales.ts sales and finance report TSV downloads (gzipped)
users.ts team users, invitations
hints.ts `_meta.mint` context-group hints (`workMeta`)
app-labels.ts start-time app directory: app names as the review read's `appId` enum
All tools use client.request() against https://api.appstoreconnect.apple.com/v1/.... JWTs are minted on demand (ES256, 20-minute lifetime) and cached until 2 minutes before expiry. Each tool file exports handler functions and a register*Tools(server) function. index.ts imports and calls each registration function.
Every write handler takes (args, ctx) and calls mcp-utils' confirmWrite(ctx, { tool, action, message, summary, account: undefined, target, request: { method, path, body }, preview?, args, confirmToken }) after building its validated path and body and before client.request(). A client with elicitation gets a prompt; one without gets a phase-1 preview (method, path, willSend body) plus a confirmToken, and only a repeat call carrying it writes. The token binds the tool, target and { method, path, body }, so changed arguments are refused as DRAFT_CHANGED. MCP_CONFIRM_MODE / MCP_CONFIRM_ELICITATION / MCP_CONFIRM_TTL_SECONDS / MCP_CONFIRM_SECRET are documented in the README. A new write tool takes confirmToken: confirmTokenParam, ends its description with ${CONFIRM_FLOW_SENTENCE} ${CONFIRM_INJECTION_RULE} (both from mcp-utils), and gets a phase-1 / phase-2 test through tests/helpers.ts. Reads that return third-party text (customer reviews) answer through mcp-utils' untrustedResult and append UNTRUSTED_DESCRIPTION_SUFFIX to their description.
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.
- 11d ago Changed · +2 lines · +40 tokens per session bb76d69853fc
- 1mo ago Changed · -1 lines · +98 tokens per session 11e78f6d8419
- 1mo ago Changed · +10 tokens per session 51ec82189772
- 1mo ago Changed · +3 lines · +236 tokens per session 68e6d6581ecf
- 2mo ago First seen · 102 lines · 1,264 tokens per session scan A 6c8c5ca21cb1
app-store-connect-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/app-store-connect-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 1,648 tokens to every session, about $0.0066 per session on Opus 5.5. 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.
app-store-connect-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-store-connect-mcp CLAUDE.mdchrischall/app-store-connect-mcp | Instructions file | 1 | 7d ago | MIT | A | 1,648 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |