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/eddmann/whatsapp-mcp/claude-mdgit clone --depth 1 https://github.com/eddmann/whatsapp-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/eddmann/whatsapp-mcp/claude-md)<a href="https://agentmods.dev/instructions/eddmann/whatsapp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eddmann/whatsapp-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 | $0.02608 | $0.02608 |
| Opus 5 | $0.01304 | $0.01304 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
whatsapp-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 5d 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 — 260 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.
Overview
WhatsApp MCP is a Go-based Model Context Protocol (MCP) server that connects to WhatsApp via whatsmeow, persists messages/chats to SQLite with FTS5, and exposes MCP tools over stdio for AI assistants like Claude/Cursor.
Build Commands
Standard Build
make build
Builds with CGO enabled and SQLite FTS5 support to bin/whatsapp-mcp. CGO is required for go-sqlite3.
Build and Run
make run
Builds and executes the binary. On first run, displays a QR code for WhatsApp pairing.
Clean
make clean
Removes the compiled binary.
Format
make format
Formats Go source code using go fmt.
Alternative Build (without Makefile)
CGO_ENABLED=1 go build -tags "sqlite_fts5" -o bin/whatsapp-mcp ./cmd/whatsapp-mcp
Architecture
Core Components
cmd/whatsapp-mcp/main.go
- Entry point: initializes store, WhatsApp client, services, and MCP server
- Registers 7 MCP tools covering chats, messages, search, messaging, media, and status
- Handles graceful shutdown (SIGINT/SIGTERM) to disconnect WhatsApp and close DBs
- Runs WhatsApp connection in background goroutine with QR authentication
- Serves MCP over stdio using mark3labs/mcp-go
Tools registered:
- Chat management:
list_chats - Message operations:
list_messages,search_messages(with date filters),catch_up(intelligent activity summary) - Messaging:
send_message(unified tool for text, media, or both with fuzzy name matching and reply/threading) - Media:
download_media - Status:
get_connection_status
internal/wa/client.go
- Wraps whatsmeow.Client with store integration
- Provides core WhatsApp client initialization and handler registration
internal/wa/sync.go
- Event handlers:
handleMessagepersists incoming messages,handleHistorySyncbackfills history - Processes WhatsApp events and syncs to local database
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.
- 5d ago First seen · 260 lines · 2,608 tokens per session scan A 92c69ef52f58
whatsapp-mcp CLAUDE.md is an instructions file published in the GitHub repository eddmann/whatsapp-mcp (5 stars, last pushed 10mo ago), licensed MIT. It adds 2,608 tokens to every session, about $0.0130 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
LIA-Assistant AGENTS.md
AGENTS.md instructions for jgouviergmail/LIA-Assistant, covering agents.md, project overview, build & development commands, full setup (backend + frontend + git hooks) and stop.
LIA-Assistant CLAUDE.md
Claude Code instructions for jgouviergmail/LIA-Assistant, covering claude.md, project overview, build & development commands, full setup (backend + frontend + git hooks) and stop.
agentor copilot-instructions.md
Instructions for CelestoAI/agentor: Read AGENTS.md in the repository root. It is the single source of contributor guidance for this project — architecture, development setup, code style, testing, and CI — and applies to Copilot exactly as written.
cloakbrowser-mcp copilot-instructions.md
Copilot instructions for swimmwatch/cloakbrowser-mcp: Follow AGENTS.md for project-wide coding, testing, documentation, changelog, and commit rules.
med-paper-assistant AGENTS.md
AGENTS.md instructions for u9401066/med-paper-assistant, covering agents.md - vs code copilot agent 指引, 核心價值：逐步多輪演進, 運行模式, 檔案保護（normal/research） and 專案規則.
med-paper-assistant copilot-instructions.md
Copilot instructions for u9401066/med-paper-assistant, covering copilot 指令（quick reference）, 核心價值, 雙模式心智模型, 模式（操作前必查 .copilot-mode.json） and 關鍵規則.