Borrowing it
Nothing to install: this file belongs to kubachour/mobile-growth-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/kubachour/mobile-growth-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/kubachour/mobile-growth-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/kubachour/mobile-growth-mcp/claude-md)<a href="https://agentmods.dev/instructions/kubachour/mobile-growth-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kubachour/mobile-growth-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/kubachour/mobile-growth-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kubachour/mobile-growth-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 | $0.01184 | $0.01184 |
| Opus 5 | $0.00592 | $0.00592 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
mobile-growth-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 10d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Editor
Overview
A platform where users connect their LLM (Claude, ChatGPT, Gemini) to a curated mobile-growth knowledge base + analytical skills. For Meta data, users install Meta's official Meta Ads MCP / AI connector — this MCP intentionally does not ship Meta API tools (avoids unofficial-API risk). Google Ads is supported directly via this MCP's local tools. Backed by curated industry knowledge (shared) and per-account audit data (scoped).
Focused on mobile campaigns, especially subscription apps.
Architecture
Three knowledge layers:
| Layer | What | Storage | Retrieval |
|---|---|---|---|
| What Works | Industry best practices | Supabase insights + pgvector |
Hybrid RAG (semantic + keyword + RRF) via Edge Function |
| What Happened | Past audits, baselines | Supabase account_audits |
SQL, scoped by api_key |
| What Is | Live campaign data | Not stored | User's ad platform API key |
MCP server architecture: The npm package (mobile-growth-mcp) runs locally via stdio. KB tools (search, list, get) are proxied through the Supabase Edge Function /functions/v1/mcp using JSON-RPC + x-api-key header. Google Ads tools run locally (token never leaves user's machine). Tool definitions are fetched dynamically from the Edge Function on startup — adding a tool server-side makes it available to all users without republishing npm. Meta API tools were removed — Meta data flows in via Meta's official AI connector (separate MCP) or pasted CSV exports.
Auth: Per-person API key (me_ prefix, SHA-256 hashed). Generate with ./scripts/generate-api-key.sh "Name". Users only need API_KEY env var (+ optional Google Ads OAuth credentials). No SUPABASE_URL/SUPABASE_ANON_KEY needed for end users.
Tech Stack
- Database: Supabase (PostgreSQL + pgvector + pg_trgm)
- Embeddings: OpenAI
text-embedding-3-small(1536d), generated during ingestion + query-time in search Edge Function - Interfaces: MCP stdio server (npm, proxies KB to Edge Function) + Edge Function (JSON-RPC MCP endpoint)
- Auth: Per-person API key (SHA-256 hashed, revocable)
- Monorepo: npm workspaces with TypeScript
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.
- 10d ago First seen · 88 lines · 1,184 tokens per session scan A f32c5fb5713e
mobile-growth-mcp CLAUDE.md is an instructions file published in the GitHub repository kubachour/mobile-growth-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,184 tokens to every session, about $0.0059 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
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.