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 skills add JOSETRA44/wacon-mcp --skill wacon-whatsappgit clone --depth 1 https://github.com/JOSETRA44/wacon-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/skills/josetra44/wacon-mcp/wacon-whatsapp)<a href="https://agentmods.dev/skills/josetra44/wacon-mcp/wacon-whatsapp"><img src="https://agentmods.dev/badge/skills/josetra44/wacon-mcp/wacon-whatsapp/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/skills/josetra44/wacon-mcp/wacon-whatsapp"><img src="https://agentmods.dev/badge/skills/josetra44/wacon-mcp/wacon-whatsapp.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 | $0.00157 | $0.04135 |
| Opus 5.5 | $0.00063 | $0.01654 |
| Sonnet 5.5 | $0.00031 | $0.00827 |
| Haiku 4.5 | $0.00016 | $0.00413 |
Grade A, and why
wacon-whatsapp 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wacon — WhatsApp con la voz del usuario
Wacon expone el WhatsApp real del usuario vía MCP. Enviar un mensaje es actuar en nombre de una persona real ante otra persona real: la meta no es redactar bien, es sonar exactamente como el usuario suena con ese contacto. Un mensaje demasiado formal a su mejor amigo delata a la IA tan rápido como un error.
Si usas la CLI en vez del MCP
Algunos agentes prefieren la terminal. Perfecto — pero añade siempre --json:
wacon inbox --json # ✅ objeto limpio, cero códigos ANSI
wacon inbox # ❌ pensado para humanos: colores que ensucian tu contexto
Con --json el comando imprime el objeto tal cual y los errores llegan como
{"ok":false,"error":"..."} con código de salida 1. Funciona en inbox,
brief, commitments, chats, read, search, resolve, targets,
status, doctor y demás comandos de datos.
wacon chat y wacon chat ultra (la app de pantalla completa) son la
excepción: son interactivos y solo para humanos — no los lances, se
quedarían bloqueados. Para todo lo tuyo usa el MCP o los comandos con --json.
Conexión
- Tools disponibles si el MCP
waconestá registrado (claude mcp add wacon -- wacon mcp). - Si un tool falla, llama
whatsapp_status. Si el estado no esconnected, usawhatsapp_loginy muéstrale el QR al usuario (imagen) para que lo escanee desde su teléfono. La sesión persiste después. - Los chats se identifican por JID (
[email protected], grupos[email protected]). Si solo tienes un nombre, resuélvelo consearch_contacts.
El workflow obligatorio para responder
Nunca envíes a ciegas. La forma más eficiente es una sola llamada:
prepare_reply(chat, situation) arma TODO el briefing de una vez y ahorra
tokens (reemplaza 5 llamadas): la persona global del usuario, los hechos de
la persona (dim 1: quién es, gustos, fechas) + huecos por descubrir, la
dinámica y estilo (dim 2: emojis, formalidad, tuteo/usted, bromas internas,
qué evitar), los últimos mensajes, el recall de memoria relevante, y —solo si el
chat está etiquetado como especial— el consejo del playbook (NotebookLM) con
citas. Activa "escribiendo…" mientras procesa. Pásale situation (qué quieres
lograr) para habilitar el recall y el playbook.
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 Changed · +23 lines 781d00d04257
- 2mo ago First seen · 267 lines · 157 tokens per session scan A 584a1fdc1b15
wacon-whatsapp is a skill published in the GitHub repository JOSETRA44/wacon-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 157 tokens to every session and 4,135 once invoked, about $0.0006 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.
wacon-whatsapp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wacon-whatsappJOSETRA44/wacon-mcp | Skill | 2 | 5d ago | MIT | A | 157 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 5d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 490 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 375 | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| frontmcp-setupagentfront/frontmcp | Skill | 150 | today | Apache-2.0 | A | 176 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 132 | 21d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| x-use-reviewihuzaifashoukat/x-use | Skill | 182 | 2d ago | MIT | A | 56 | Claude Code |