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/AGENTS.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/instructions/sumioshi/whatsapp-automation/agents-md)<a href="https://agentmods.dev/instructions/sumioshi/whatsapp-automation/agents-md"><img src="https://agentmods.dev/badge/instructions/sumioshi/whatsapp-automation/agents-md/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/instructions/sumioshi/whatsapp-automation/agents-md"><img src="https://agentmods.dev/badge/instructions/sumioshi/whatsapp-automation/agents-md.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 | $0.02040 | $0.02040 |
| Opus 5.5 | $0.00816 | $0.00816 |
| Sonnet 5.5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
whatsapp-automation AGENTS.md 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.
envio via curl na API. How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruções do projeto (Codex e outros agentes)
WhatsApp deste projeto: <slug-do-grupo> (). Consulte o histórico via MCP
whatsapp-collector usando esse slug (ex: resumo_do_dia, ler_mensagens, buscar).
Detalhes em .claude/whatsapp.json. As skills do projeto estão em .agents/skills/
(mesmo padrão Agent Skills; fonte em .claude/skills/).
Este arquivo é o espelho do CLAUDE.md pra agentes fora do Claude Code. A skill
plantao possui um adaptador em .agents/skills/plantao/: ele usa o mecanismo
persistente de monitoramento disponível no runtime. Se o runtime atual não conseguir
despertar o agente quando chegar um evento, não declare que o plantão foi armado;
ofereça checar novidades sob demanda ou ligar alertar_chat (notificação no Mac).
Memória do projeto = memória do Claude Code (leia antes de começar)
"Memória do projeto" e "memórias do Claude" são a MESMA coisa: .memoria/ é um link local para
~/.claude/projects/<este projeto>/memory, a memória que o Claude Code grava (fora do git porque
tem dado de cliente). Decisões, incidentes e preferências do operador que não estão no código
ficam lá. Se o link existir, leia .memoria/MEMORY.md no início: é o índice, cada linha é um fato
com um gancho, e o arquivo apontado tem o detalhe. Abra só os que tocam a tarefa (o índice tem
~6 mil tokens, a memória inteira ~60 mil); se o operador pedir pra ler tudo, leia. O que estiver
lá vale como contexto, mas confira no código antes de afirmar que uma função, flag ou arquivo
citado ainda existe.
Pra registrar algo novo (correção do operador, decisão de projeto, incidente), crie um arquivo
por fato no mesmo formato dos que já estão lá (frontmatter com name, description e
metadata.type; corpo com o fato, Why: e How to apply:), antes confira se já não existe
um sobre o assunto, e acrescente uma linha em MEMORY.md. Não grave o que o git ou o código já
contam.
Config por runtime
Cada agente lê a sua pasta, mas o comportamento esperado é o mesmo nos três:
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 · +43 lines · +886 tokens per session 67a8c5c06adc
- 2mo ago First seen · 75 lines · 1,154 tokens per session scan A 07d009f88ffa
whatsapp-automation AGENTS.md is an instructions file published in the GitHub repository sumioshi/whatsapp-automation (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,040 tokens to every session, about $0.0082 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.
whatsapp-automation AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| whatsapp-automation AGENTS.mdsumioshi/whatsapp-automation | Instructions file | 2 | 7d ago | Apache-2.0 | A | 2,040 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 281k | yesterday | MIT | A | 4,335 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |