whatsapp-automation: Skill for Claude Code

.claude/skills/voz-do-operador/SKILL.md

voz-do-operador is a skill for Claude Code from sumioshi/whatsapp-automation. It costs 136 tokens per session (2,912 once invoked), scanned A, original, Apache-2.0.

Um formulário para descrever como uma pessoa escreve mensagens no WhatsApp, usando exemplos e medições do seu histórico real.

In plain words
What is it for?
Serve para medir padrões de escrita anteriores à automação e orientar mensagens que sigam a voz real do operador.
Why use it?
Evita inventar um estilo de escrita ou fazer a automação aprender com mensagens que ela própria já enviou.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sumioshi/whatsapp-automation's own configuration. It tells Claude Code how to work on whatsapp-automation 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-automation configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/sumioshi/whatsapp-automation/main/.claude/skills/voz-do-operador/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sumioshi/whatsapp-automation

Made for: Claude Code.

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 voz-do-operador

README.md
[![agentmods](https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/voz-do-operador/github.svg)](https://agentmods.dev/skills/sumioshi/whatsapp-automation/voz-do-operador)
Your own site
<a href="https://agentmods.dev/skills/sumioshi/whatsapp-automation/voz-do-operador"><img src="https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/voz-do-operador/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 voz-do-operador

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumioshi/whatsapp-automation/voz-do-operador"><img src="https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/voz-do-operador.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,912 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00136 $0.02912
Opus 5.5 $0.00054 $0.01165
Sonnet 5.5 $0.00027 $0.00582
Haiku 4.5 $0.00014 $0.00291

Measured 2d ago against content hash 685cd446fbac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

voz-do-operador 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (extrair-voz.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/voz-do-operador/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voz do operador — MOLDE

Este arquivo é um formulário, não um perfil. Todo campo {{assim}} precisa ser substituído por um número ou exemplo tirado do SEU histórico. Não invente valores, e não deixe placeholder pela metade: um perfil meio preenchido é pior que nenhum, porque parece autoridade e não é.

Como preencher: README.md nesta pasta.

Por que medir em vez de descrever

Ninguém descreve a própria escrita com precisão — sai sempre a versão idealizada, mais articulada e mais educada do que a real. O jeito que funciona é medir: as mensagens que você já mandou são a amostra, e elas não mentem sobre quantas vírgulas você usa nem sobre quantas vezes você repete a mesma abertura.

Recorte obrigatório: só mensagens anteriores ao dia em que a automação começou a enviar por você. Depois disso as mensagens fromMe são da IA, e o perfil passaria a aprender o próprio eco.


COMO USAR (vale mesmo depois de preencher)

Os percentuais não são regra por mensagem. São a média que a conversa inteira deve ter. Aplicar um número a cada balão produz uniformidade, e uniformidade é o que denuncia texto de máquina — inclusive uniformidade "informal".

Espere que o mesmo traço varie muito entre chats: é assim que gente escreve. Preencha a faixa observada, não só a média:

traço chat mais solto chat mais formal
balão com ponto final {{X}}% {{Y}}%
vírgula {{X}}% {{Y}}%

Decida caso a caso, com três eixos:

  1. Quem é o interlocutor. Cliente novo ou institucional → mais formal. Parceiro de longa data → mais solto.
  2. A temperatura do assunto. Status corriqueiro → solto. Dinheiro, prazo estourado, erro que custou caro → sobe o registro, mesmo num chat informal.
  3. Onde a conversa está. Primeiro contato e proposta → mais cuidado. Meio da execução → mais solto.

Espelhe o interlocutor e varie de propósito dentro da mesma conversa. Se os últimos balões saíram sem ponto final, o próximo pode ter.

Read the full file on GitHub · 284 lines

Files

What ships with it

2 files 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.

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. 2d ago Changed · +7 lines 685cd446fbac
  2. 2mo ago First seen · 277 lines · 136 tokens per session scan A 70200b6bb427

Subscribe to this mod's changes

voz-do-operador is a skill published in the GitHub repository sumioshi/whatsapp-automation (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 136 tokens to every session and 2,912 once invoked, about $0.0005 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.

Related

voz-do-operador compared with skills from other repositories

voz-do-operador next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
voz-do-operadorsumioshi/whatsapp-automationSkill27d agoApache-2.0A136Claude Code
quick-capturevscarpenter/gsd-task-managerSkill41todayMITA0Claude Code, Codex
triage-inboxvscarpenter/gsd-task-managerSkill41todayMITA0Claude Code, Codex
todoxbeydemirfurkan/todoxSkill24d agoMITA63Claude Code
lastestlas-team/lastestSkill222d agononeA33Claude Code, Codex
lastestlas-team/lastestSkill222d agononeA0Claude Code, Codex
Lastest design systemlas-team/lastestSkill222d agononeA39Claude Code, Codex