Borrowing it
Nothing to install: this file belongs to sumioshi/whatsapp-automation. 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/sumioshi/whatsapp-automation/main/.claude/skills/run-whatsapp-automation/SKILL.mdgit clone --depth 1 https://github.com/sumioshi/whatsapp-automationWrote 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/sumioshi/whatsapp-automation/run-whatsapp-automation)<a href="https://agentmods.dev/skills/sumioshi/whatsapp-automation/run-whatsapp-automation"><img src="https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/run-whatsapp-automation/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/sumioshi/whatsapp-automation/run-whatsapp-automation"><img src="https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/run-whatsapp-automation.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 | $0.00000 | $0.05444 |
| Opus 5.5 | $0.00000 | $0.02178 |
| Sonnet 5.5 | $0.00000 | $0.01089 |
| Haiku 4.5 | $0.00000 | $0.00544 |
Grade A, and why
run-whatsapp-automation scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> vazio NÃO significa serviços fora — confirme sempre pelos smoke `curl` How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run: WhatsApp Automation
Coleta conteúdo de grupos de WhatsApp (áudio/vídeo/imagem/documento/texto) e expõe
tudo pra IA. São 5 processos: wa-collector (daemon Baileys), wa-panel
(Next.js em :3000), wa-transcriber (serviço MLX em :4320), wa-notifier
(notificação de mensagens de cliente, ver seção abaixo) e o MCP server
(stdio, sob demanda). O MCP é dirigido pelo driver abaixo. Tools de escrita
preparar_resposta (contexto antes de redigir) e revisar_texto (revisa sem
enviar) entram no pipeline de envio — ver seção "Regra: enviar mensagem no
grupo" abaixo.
Como os 3 primeiros rodam: em dev local (o caso atual) é
npm run devna raiz, que sobe os três viaconcurrently— não pm2. Em produção é pm2 (ecosystem.config.cjs). Os dois caminhos existem; veja "Run" abaixo.pm2 lsvazio NÃO significa serviços fora — confirme sempre pelos smokecurl(:3000 / :4310 / :4320), não pelo pm2.
Plataforma: macOS Apple Silicon. A transcrição usa
mlx_whisper(MLX), que só roda em Apple Silicon — em Linux o coletor e o painel sobem, mas o transcriber não. Paths neste arquivo são relativos à raiz do repo.
Dois coletores, dois servidores MCP
whatsapp-collector= coletor PRINCIPAL (número business, clientes). É o default.whatsapp-pessoal= coletor PESSOAL (2º container na Railway, WhatsApp pessoal do operador). Mesmas tools, mesmo código, outro trio de acesso. Use quando o operador disser "no pessoal", "meu WhatsApp pessoal", ou o chat não existir no principal. Contas diferentes → slugs diferentes;listar_gruposem cada um. Plantão no pessoal:PLANTAO_CLOUD=pessoalnoplantao-stream.sh.
⚠️ Regra: enviar mensagem (grupo ou DM) → humanizar SEMPRE
Sempre que o usuário pedir para enviar, responder ou redigir uma mensagem num
grupo (via responder, responder_midia com legenda, pelo painel, ou pela API de controle :4310):
Pipeline de envio, nesta ordem: preparar_resposta(grupo) → skill de voz do operador
(voz-do-dono nesta máquina; molde voz-do-operador) → comunicacao-cliente (conduta) →
no modo confirmar, revisar_texto e mostrar ao operador o texto já revisado → responder
com candidatos (2-3 versões) ou baloes. humanizer não entra em balão de conversa. Se a revisão recusar, reescreva seguindo sugestoes; não use revisao: 'ignorar'
sem OK explícito do operador.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +53 lines 184810a625e1
- 2mo ago First seen · 240 lines · 0 tokens per session scan A e8b8192cd56e
run-whatsapp-automation is a skill published in the GitHub repository sumioshi/whatsapp-automation (2 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,444 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
run-whatsapp-automation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-whatsapp-automationsumioshi/whatsapp-automation | Skill | 2 | 7d ago | Apache-2.0 | A | 0 | Claude Code |
| quick-capturevscarpenter/gsd-task-manager | Skill | 41 | today | MIT | A | 0 | Claude Code, Codex |
| triage-inboxvscarpenter/gsd-task-manager | Skill | 41 | today | MIT | A | 0 | Claude Code, Codex |
| todoxbeydemirfurkan/todox | Skill | 2 | 4d ago | MIT | A | 63 | Claude Code |
| lastestlas-team/lastest | Skill | 22 | 2d ago | none | A | 33 | Claude Code, Codex |
| lastestlas-team/lastest | Skill | 22 | 2d ago | none | A | 0 | Claude Code, Codex |
| Lastest design systemlas-team/lastest | Skill | 22 | 2d ago | none | A | 39 | Claude Code, Codex |