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/pnizer/wweb-mcp/claude-mdgit clone --depth 1 https://github.com/pnizer/wweb-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/pnizer/wweb-mcp/claude-md)<a href="https://agentmods.dev/instructions/pnizer/wweb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pnizer/wweb-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 | $0.01221 | $0.01221 |
| Opus 5 | $0.00611 | $0.00611 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
wweb-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 4d 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 — 136 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.
Project Overview
WhatsApp Web MCP is a Node.js/TypeScript application that bridges WhatsApp Web with AI models through the Model Context Protocol (MCP). It provides two main deployment modes:
- WhatsApp API Server (
--mode whatsapp-api) - Standalone REST API server - MCP Server (
--mode mcp) - Direct MCP protocol implementation with two sub-modes:standalone- Direct WhatsApp Web client connectionapi- Connects to a WhatsApp API server
Development Commands
Essential Commands
# Build the project
npm run build
# Run tests
npm test
npm run test:watch # Watch mode for development
npm run test:coverage # Generate coverage report
# Linting and formatting
npm run lint
npm run lint:fix # Auto-fix linting issues
npm run format # Format with Prettier
npm run validate # Run lint + test together
Running the Application
# Development mode with auto-reload
npm run dev
# Production mode
npm run build && npm start
# Run specific modes
npx . --mode whatsapp-api --api-port 3001
npx . --mode mcp --mcp-mode standalone --transport sse --sse-port 3002
Architecture
Core Components
- main.ts - Application entry point with CLI argument parsing and server initialization
- whatsapp-service.ts - Core business logic for WhatsApp interactions using whatsapp-web.js
- whatsapp-api-client.ts - HTTP client for connecting to WhatsApp API server
- mcp-server.ts - MCP protocol implementation with tools and resources
- api.ts - Express REST API router
- whatsapp-client.ts - WhatsApp Web client factory and configuration
Key Design Patterns
- Service Layer Pattern - WhatsAppService abstracts WhatsApp operations
- Factory Pattern - createWhatsAppClient and createMcpServer for component creation
- Adapter Pattern - WhatsAppApiClient adapts REST API to service interface
- Configuration Object Pattern - WhatsAppConfig and McpConfig for dependency injection
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.
- 4d ago First seen · 136 lines · 1,221 tokens per session scan A 6e5753700ab8
wweb-mcp CLAUDE.md is an instructions file published in the GitHub repository pnizer/wweb-mcp (44 stars, last pushed 1y ago), licensed MIT. It adds 1,221 tokens to every session, about $0.0061 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 2026-08-30.
Other instructions, from other repositories
go-whatsapp-web-multidevice AGENTS.md
AGENTS.md instructions for aldinokemal/go-whatsapp-web-multidevice, covering project knowledge base, structure, where to look, code map and conventions.
open-bsp-api CLAUDE.md
Claude Code instructions for matiasbattocchia/open-bsp-api, covering claude.md, project overview, local checks must match ci (deno), debugging production edge functions and timestamps.
wa_llm AGENTS.md
AGENTS.md instructions for ilanbenb/wa_llm, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
whatsapp-mcp-extended CLAUDE.md
Instructions for FelixIsaac/whatsapp-mcp-extended, covering claude.md, project overview, architecture, commands and docker (recommended).
whatsapp-mcp-extended AGENTS.md
Instructions for FelixIsaac/whatsapp-mcp-extended, covering agents.md — developer & ai agent guidelines, 🎯 architecture overview, ⚠️ critical rules for ai agents, 🧪 quick test commands and run go bridge tests.
harken CLAUDE.md
Claude Code instructions for montezuma-p/harken, covering claude.md — harken, commands, inviolable rules, commits and toolchain.