agentmods.dev

whatsapp-mcp: Instructions file for Codex

AGENTS.md

whatsapp-mcp AGENTS.md is an instructions file for Codex, OpenCode from rodrigopg/whatsapp-mcp. It costs 1,064 tokens per session, scanned A, original, MIT.

Project instructions for a community WhatsApp server that connects a Go bridge to WhatsApp and a Python server using the Model Context Protocol, or MCP, a standard way for AI tools to access services.

In plain words
What is it for?
Use them when changing the Go bridge, Python MCP server, audio transcription, deployment, REST API binding, or related WhatsApp features.
Why use it?
They tell developers which context files to read and enforce safety rules for the API, authentication, rebuilding, deployment, and transcription.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is rodrigopg/whatsapp-mcp's own configuration. It tells Codex and OpenCode how to work on whatsapp-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whatsapp-mcp configures →

not rated 4repo +1 changed 4d ago A scan 1,064 tokens original MIT
View source ↗ rodrigopg/whatsapp-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to rodrigopg/whatsapp-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.

Copy the file
curl -O https://raw.githubusercontent.com/rodrigopg/whatsapp-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rodrigopg/whatsapp-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for whatsapp-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rodrigopg/whatsapp-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/rodrigopg/whatsapp-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rodrigopg/whatsapp-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rodrigopg/whatsapp-mcp/agents-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.

agentmods 80×15 button for whatsapp-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rodrigopg/whatsapp-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rodrigopg/whatsapp-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,064 This file is loaded in full into every session.
When invoked 1,064 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01064 $0.01064
Opus 5.5 $0.00426 $0.00426
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00106 $0.00106

Measured 4d ago against content hash cbc9958fe41c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whatsapp-mcp AGENTS.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.

AGENTS.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WhatsApp MCP Server

MCP server pra WhatsApp pessoal. Bridge Go/whatsmeow (whatsapp-bridge/) + servidor MCP Python (whatsapp-mcp-server/), SQLite local, transcrição de áudio opt-in.

Carregar contexto antes de trabalhar

Área Arquivo
Bridge Go (whatsmeow, REST, history sync, mídia, segurança) .claude/context/bridge-go.md
Servidor MCP Python (tools, busca, LID) .claude/context/mcp-python.md
Transcrição (whisper local/API, backfill, recovery, sweep) .claude/context/transcription.md
Deploy/operação (VPS systemd, launchd local, build, install.sh, DNS, git) .claude/context/deploy.md

Tarefa multi-área: leia os arquivos relevantes em paralelo.

Regras inegociáveis

  • Go 1.26+ (casa com go.mod); recompilar binário após mudar main.go — go run é só dev. CGO impede cross-compile do macOS pra Linux/VPS — compilar direto na VPS (tem Go+gcc lá).
  • REST API liga 127.0.0.1 por padrão; BIND_ADDR=<ip> pra expor além de loopback exige API_AUTH_TOKEN setado (a bridge recusa subir sem token nesse caso) — nunca bind não-loopback sem token, mesmo em rede privada (Tailscale/VPN não é substituto de auth).
  • safeMediaPath rejeita componentes com separadores/.. — não sanitizar silenciosamente.
  • Re-parear/re-sync: StoreMessage preserva content existente via COALESCE(NULLIF(...)) (não sobrescreve transcrição com string vazia do sync) — mas faça backup de messages.db/whatsapp.db antes de qualquer re-pareamento de qualquer forma, é operação real de produção.
  • Transcrição é opt-in; sem engine, sweep deve ser no-op (não marcar áudios).
  • transcription.env nunca commitado (gitignored).
  • Repo próprio (independente do projeto original): origin = rodrigopg/whatsapp-mcp.

Checklist antes de abrir PR

  • go build -o whatsapp-bridge . compila; go test ./... passa.
  • python3 -m unittest test_transcribe -v passa.
  • Mudou main.go? Binário recompilado e bridge reiniciada — local: launchctl kickstart -k; VPS: go build na própria VPS (CGO não cross-compila) + systemctl restart whatsapp-bridge-*.
  • Sem path pessoal/secret vazando (transcription.env, API keys).
  • Mudou comportamento de sync/escrita? Conferir impacto em transcrições existentes.
  • README/install.sh coerentes se mudou onboarding (versão Go, env vars, troubleshooting).
  • PR contra rodrigopg/main.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 4d ago Changed · +6 tokens per session cbc9958fe41c
  2. 13d ago Changed 4cb6233da3f4
  3. 21d ago Changed · +9 lines · +193 tokens per session 3ef8519caa86
  4. 25d ago Changed · +3 tokens per session 624c0bcba2bb
  5. 1mo ago First seen · 53 lines · 862 tokens per session scan A f64693831dea

Subscribe to this mod's changes

whatsapp-mcp AGENTS.md is an instructions file published in the GitHub repository rodrigopg/whatsapp-mcp (4 stars, last pushed 3d ago), licensed MIT. It adds 1,064 tokens to every session, about $0.0043 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.

Claude Codeclaude-code-pluginmcpmcp-serverwhatsapp
Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens