Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/hainrixz/whatsapp-agentkit/build-agentgit clone --depth 1 https://github.com/Hainrixz/whatsapp-agentkitWrote 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/hainrixz/whatsapp-agentkit/build-agent)<a href="https://agentmods.dev/commands/hainrixz/whatsapp-agentkit/build-agent"><img src="https://agentmods.dev/badge/commands/hainrixz/whatsapp-agentkit/build-agent.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00633 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
build-agent 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 5d 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.
What it actually says
Lee el archivo CLAUDE.md completo. Contiene todas las instrucciones detalladas.
Ejecuta el flujo de onboarding de AgentKit siguiendo las 5 fases EN ORDEN:
FASE 1 — Bienvenida y verificación del entorno
- Muestra el mensaje de bienvenida
- Verifica Python >= 3.11
- Crea las carpetas necesarias (agent/, agent/providers/, config/, knowledge/, tests/)
- Genera requirements.txt e instala dependencias
- Crea .env base
FASE 2 — Entrevista del negocio
- Haz las 10 preguntas UNA POR UNA
- Espera respuesta antes de continuar a la siguiente
- PREGUNTA 9: el usuario elige su proveedor de WhatsApp (Zernio o Meta Cloud API directo)
- PREGUNTA 10: pide las credenciales específicas del proveedor elegido
- Zernio: ZERNIO_API_KEY + ZERNIO_WEBHOOK_SECRET
- Meta: META_ACCESS_TOKEN + META_PHONE_NUMBER_ID + META_VERIFY_TOKEN + META_APP_SECRET
- Si no tiene número de WhatsApp todavía, ofrécele el sandbox de Zernio
- Guarda todas las respuestas para la Fase 3
FASE 3 — Generación del agente
- Genera config/business.yaml con datos del negocio
- Genera config/prompts.yaml con system prompt poderoso y específico
- Si hay archivos en /knowledge, léelos e incorpóralos al prompt
- Genera agent/providers/ con el proveedor elegido (base.py + init.py + adaptador)
- Genera agent/main.py (FastAPI + webhook, firma verificada, BackgroundTasks, dedup)
- Genera agent/brain.py (Claude API)
- Genera agent/memory.py (historial + tabla de eventos procesados)
- Genera agent/tools.py (herramientas según caso de uso)
- Genera tests/test_local.py (simulador de chat)
- Genera Dockerfile, docker-compose.yml y .dockerignore
- Configura .env con WHATSAPP_PROVIDER y las API keys del usuario
FASE 4 — Testing local
- Ejecuta python tests/test_local.py
- El usuario chatea con su agente en la terminal
- Verifica que el servidor arranca y que GET / responde status ok
- Si hay ajustes, modifica prompts.yaml y repite
- No avanza sin aprobación del usuario
FASE 5 — Deploy a Railway
- Solo si el usuario quiere
- Build Docker + instrucciones de Railway
- Configuración de webhook específica para el proveedor elegido
- Explicarle la ventana de 24 horas de WhatsApp
REGLAS:
- Habla siempre en español
- Una pregunta a la vez
- Nunca hardcodees API keys
- No avances de fase sin confirmación
- El agente debe funcionar antes de hablar de deploy
- Genera SOLO el adaptador del proveedor elegido, no los dos
- No cambies el modelo de Claude por tu cuenta para ahorrar: es decisión del 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.
- 5d ago First seen · 56 lines · 0 tokens per session scan A 515d134d2452
build-agent is a command published in the GitHub repository Hainrixz/whatsapp-agentkit (481 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 633 tokens. 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.
Other commands, from other repositories
coding-prompt
You are continuing work on a long-running autonomous development task. This is a FRESH context window - you have no memory of previous sessions.
initializer-prompt
You are the FIRST agent in a long-running autonomous development process. Your job is to set up the foundation for all future coding agents.
MIGRATE_DESIGN
Design doc for the migration tool PR. Author: Sol ([email protected]). Co-authored-by: wakesync.
os-meeting
快速创建和管理AI团队会议.
branch-cleanup
Clean up merged and stale branches locally and remotely.
audit-accessibility
Audit web page or component for WCAG accessibility compliance.