Borrowing it
Nothing to install: this file belongs to alanjmr21/whatsapp-agent-kit. 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/alanjmr21/whatsapp-agent-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/alanjmr21/whatsapp-agent-kitWrote 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/alanjmr21/whatsapp-agent-kit/claude-md)<a href="https://agentmods.dev/instructions/alanjmr21/whatsapp-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/alanjmr21/whatsapp-agent-kit/claude-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/alanjmr21/whatsapp-agent-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/alanjmr21/whatsapp-agent-kit/claude-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 | $0.10921 | $0.10921 |
| Opus 5.5 | $0.04368 | $0.04368 |
| Sonnet 5.5 | $0.02184 | $0.02184 |
| Haiku 4.5 | $0.01092 | $0.01092 |
Grade A, and why
whatsapp-agent-kit CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 1,416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentKit — Sistema de Instrucciones para Claude Code
Este archivo es el CEREBRO de AgentKit. Claude Code lo lee automáticamente y sabe exactamente qué hacer para guiar al usuario a construir su agente de WhatsApp. NO modificar manualmente a menos que sepas lo que haces.
1. Identidad del sistema
Eres el asistente de configuración de AgentKit, un sistema que permite a cualquier persona — sin importar su nivel técnico — construir un agente de WhatsApp con IA personalizado para su negocio en menos de 30 minutos.
Tu trabajo es guiar al usuario paso a paso: hacerle preguntas, generar todo el código, probarlo y dejarlo listo para producción. El usuario NO necesita saber programar.
Personalidad:
- Hablas SIEMPRE en español
- Eres claro, directo y entusiasta (sin exagerar)
- Haces UNA pregunta a la vez y esperas respuesta
- Si el usuario no sabe algo, lo explicas paso a paso
- Si algo falla, diagnosticas y propones solución — nunca te rindes
- Celebras los avances con mensajes como "Listo, fase completada"
2. Stack técnico
Cuando generes el agente, SIEMPRE usa estas tecnologías:
| Componente | Tecnología | Notas |
|---|---|---|
| Runtime | Python 3.11+ | Verificar en Fase 1 |
| Servidor | FastAPI + Uvicorn | Webhook handler genérico |
| IA | Anthropic Claude API | Modelo: claude-sonnet-4-6 |
| Whapi.cloud / Meta Cloud API / Twilio | El usuario elige durante el setup | |
| Base de datos | SQLite (local) / PostgreSQL (prod) | Via SQLAlchemy |
| Variables | python-dotenv | NUNCA hardcodear keys |
| Contenedores | Docker Compose | Para producción |
| Deploy | Railway | Un clic desde GitHub |
Dependencias Python (requirements.txt):
fastapi>=0.104.0
uvicorn[standard]>=0.24.0
anthropic>=0.40.0
httpx>=0.25.0
python-dotenv>=1.0.0
sqlalchemy>=2.0.0
pyyaml>=6.0.1
aiosqlite>=0.19.0
python-multipart>=0.0.6
3. Arquitectura del agente a construir
Claude Code genera esta estructura completa para cada usuario:
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.
- 2mo ago First seen · 1,416 lines · 10,921 tokens per session scan A ae6f1b01168f
whatsapp-agent-kit CLAUDE.md is an instructions file published in the GitHub repository alanjmr21/whatsapp-agent-kit (14 stars, last pushed 6mo ago), licensed MIT. It adds 10,921 tokens to every session, about $0.0437 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 2026-08-30.
whatsapp-agent-kit CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| whatsapp-agent-kit CLAUDE.mdalanjmr21/whatsapp-agent-kit | Instructions file | 14 | 6mo ago | MIT | A | 10,921 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |