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/commands/plantao.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/commands/sumioshi/whatsapp-automation/plantao)<a href="https://agentmods.dev/commands/sumioshi/whatsapp-automation/plantao"><img src="https://agentmods.dev/badge/commands/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.
<a href="https://agentmods.dev/commands/sumioshi/whatsapp-automation/plantao"><img src="https://agentmods.dev/badge/commands/sumioshi/whatsapp-automation/plantao.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 | $0.00027 | $0.00391 |
| Opus 5.5 | $0.00011 | $0.00156 |
| Sonnet 5.5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
plantao scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Senão, se um chat for informado pelo usuário, resolva o slug via API do painel (`$REPO/scripts/plantao-candidatos.sh` ou `curl $WAC_CLOUD_URL/api/groups/summary`). What it actually says
Arma um Monitor SSE da nuvem que acorda o agente a cada mensagem nova em um chat do WhatsApp, sem depender de coletor local.
Siga os passos exatamente como especificados na skill plantao:
-
Identificar o chat/slug:
- Se o projeto atual tiver
.claude/whatsapp.json, use ogrupo(slug) cadastrado lá. - Senão, se um chat for informado pelo usuário, resolva o slug via API do painel (
$REPO/scripts/plantao-candidatos.shoucurl $WAC_CLOUD_URL/api/groups/summary). - Se houver dúvida ou múltiplos candidatos, pergunte ao usuário antes de armar.
- Se o projeto atual tiver
-
Checar se o grupo está com
watch: truena nuvem:- Se
"watch": false, ative viaPOST $WAC_CLOUD_URL/api/groups{"id": "<jid>", "watch": true}.
- Se
-
Matar monitores zumbis antigos do mesmo chat.
-
Armar o Monitor SSE:
- Execute o script
plantao-stream.sh <slug> [slug...](ou--alertar) comMonitor(persistent: true)— vários chats cabem num Monitor só. - Saída imediata com código 3 = já existe plantão desse conjunto; mate o antigo em vez de armar outro.
- Execute o script
-
Confirmar ao usuário que o plantão está ativo: mensagens recebidas e respostas manuais dele (
Você (celular)) acordam o agente; o que o MCP mandou não.
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 · +1 lines 5192c21e2068
- 2mo ago First seen · 24 lines · 27 tokens per session scan A 40e66374b05b
plantao is a command published in the GitHub repository sumioshi/whatsapp-automation (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 27 tokens to every session and 391 once invoked, about $0.0001 per session on Opus 5.5. 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.
plantao compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plantaosumioshi/whatsapp-automation | Command | 2 | 7d ago | Apache-2.0 | A | 27 | Claude Code |
| vs-stopmtarcure/claude-vibe-squad | Command | 228 | 16d ago | MIT | A | 0 | Claude Code |
| recapfirst-fluke/fullstack-starter | Command | 226 | 4d ago | MIT | A | 47 | GitHub Copilot |
| resumeKastalien-Research/thoughtbox | Command | 66 | 3d ago | MIT | A | 0 | Claude Code |
| weekly-reviewskeletonarmytech/marrow-mcp | Command | 3 | 23d ago | MIT | A | 19 | Claude Code |
| configruvnet/sublinear-time-solver | Command | 93 | 2d ago | MIT | A | 0 | Claude Code |
| sessionruvnet/sublinear-time-solver | Command | 93 | 2d ago | MIT | A | 0 | Claude Code |