build-agent

build-agent is a command for Claude Code from alanjmr21/whatsapp-agent-kit. It costs 0 tokens per session (508 once invoked), scanned A, original, MIT.

An onboarding command for creating a WhatsApp business assistant with AgentKit. It reads project instructions, checks the environment, asks business questions, and generates the assistant's files and configuration.

In plain words
What is it for?
Use it to set up a Python-based WhatsApp agent, connect a selected WhatsApp provider, add business knowledge, and generate its API, memory, and configuration files.
Why use it?
It replaces a lengthy setup process with a guided sequence that collects the required business and provider details.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/alanjmr21/whatsapp-agent-kit/build-agent
Clone the repo
git clone --depth 1 https://github.com/alanjmr21/whatsapp-agent-kit

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 508 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00508
Opus 5 $0.00000 $0.00254
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 3d ago against content hash 3ec56b1cb9ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.claude/commands/build-agent.md · 50 lines

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 (Whapi/Meta/Twilio)
  • PREGUNTA 10: pide las credenciales específicas del proveedor elegido
  • 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 provider-agnostic)
  • Genera agent/brain.py (Claude API)
  • Genera agent/memory.py (SQLite + historial)
  • Genera agent/tools.py (herramientas según caso de uso)
  • Genera tests/test_local.py (simulador de chat)
  • Genera Dockerfile y docker-compose.yml
  • 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
  • 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

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 3)
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. 3d ago First seen · 50 lines · 0 tokens per session scan A 3ec56b1cb9ec

Subscribe to this mod's changes

build-agent is a command published in the GitHub repository alanjmr21/whatsapp-agent-kit (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 508 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.