whatsapp-automation: Skill for Claude Code

.agents/skills/plantao/SKILL.md

plantao is a skill for Claude Code, Codex from sumioshi/whatsapp-automation. It costs 48 tokens per session (553 once invoked), scanned A, original, Apache-2.0.

A monitoring routine for incoming WhatsApp chat messages. It finds the right chat, checks monitoring status, and watches for messages without replying automatically.

In plain words
What is it for?
Use it to monitor a WhatsApp chat or group and alert the operator when new messages arrive, subject to the runtime's monitoring support.
Why use it?
It helps an operator notice new messages without repeatedly checking the chat by hand. It also avoids duplicate monitors and ignores messages sent by the operator.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

This is sumioshi/whatsapp-automation's own configuration. It tells Claude Code and Codex 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/.agents/skills/plantao/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sumioshi/whatsapp-automation

Made for: Claude Code, Codex.

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 plantao

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sumioshi/whatsapp-automation/plantao"><img src="https://agentmods.dev/badge/skills/sumioshi/whatsapp-automation/plantao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 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 $0.00048 $0.00553
Opus 5.5 $0.00019 $0.00221
Sonnet 5.5 $0.00010 $0.00111
Haiku 4.5 $0.00005 $0.00055

Measured 2d ago against content hash 496355ea63ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plantao 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.

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/skills/plantao/SKILL.md · 48 lines

What it actually says

Plantão de mensagens WhatsApp (adaptador de runtime)

Leia completamente a skill canônica antes de agir:

<raiz-do-repo>/.claude/skills/plantao/SKILL.md (path relativo: ../../.claude/skills/plantao/SKILL.md)

Preserve dela:

  • a descoberta e confirmação do chat;
  • a resolução do slug;
  • a verificação de watch para grupos;
  • a remoção de monitores duplicados;
  • o filtro de mensagens fromMe;
  • a regra de nunca responder automaticamente.

Adaptação de runtime

As ferramentas Monitor, TaskList e TaskStop citadas na skill canônica são específicas do Claude Code. O equivalente muda por runtime:

Runtime Armar Inspecionar Encerrar
Claude Code Monitor(persistent: true, command: …) TaskList TaskStop
Qwen Code monitor(command: …, idle_timeout_ms: 600000, max_events: 10000) list_agents task_stop
Outros o mecanismo persistente de monitoramento/automação do produto — —

Em todos, o comando vigiado é o mesmo:

<raiz-do-repo>/scripts/plantao-stream.sh <slug>

Limite do Qwen Code (importante): o monitor para sozinho após idle_timeout_ms sem saída (teto 600000 ms = 10 min) ou max_events eventos. Chat quieto derruba o plantão — então, pra vigília longa, prefira /loop ou cron_create chamando novidades em intervalo, e diga ao operador qual dos dois você armou. Nunca declare plantão armado com o monitor prometendo horas.

Antes de armar, encerre o monitor anterior do mesmo chat (zumbi duplica resposta). Se o runtime não oferecer monitoramento persistente capaz de despertar o agente, não declare que o plantão foi armado: explique a limitação e ofereça novidades sob demanda ou alertar_chat (notificação no Mac).

Nunca substitua o plantão por um loop bloqueante improvisado nem envie mensagens ao chat.

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 · -3 tokens per session 496355ea63ca
  2. 2mo ago First seen · 41 lines · 51 tokens per session scan A 90150858c643

Subscribe to this mod's changes

plantao is a skill published in the GitHub repository sumioshi/whatsapp-automation (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 48 tokens to every session and 553 once invoked, about $0.0002 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

plantao compared with skills from other repositories

plantao next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
plantaosumioshi/whatsapp-automationSkill27d agoApache-2.0A48Claude Code, Codex
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