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.
git clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/planificar-tecnico)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/planificar-tecnico"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/planificar-tecnico/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/doncheli/don-cheli-sdd/planificar-tecnico"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/planificar-tecnico.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 | $0.00011 | $0.01463 |
| Opus 5 | $0.00005 | $0.00732 |
| Sonnet 5 | $0.00002 | $0.00293 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade A, and why
planificar-tecnico 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 7d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:planificar-tecnico
Objetivo
Generar un blueprint técnico (contratos API, modelos, arquitectura de servicios) desde una especificación Gherkin, incluyendo verificación de constitución y contexto técnico estructurado.
Alineado con spec-kit (github/spec-kit) — Constitution Check, Technical Context y Complexity Tracking
Uso
/dc:planificar-tecnico @specs/features/<dominio>/<Feature>.feature
Comportamiento
- Verificar Puerta 2 — El
.featuredebe tener tag@lista(pasó/dc:clarificar) - Verificar que no hay marcadores
[NECESITA CLARIFICACIÓN]pendientes - Ejecutar Chequeo de Constitución — Validar contra los principios de
reglas/constitucion.md - Documentar Contexto Técnico — Stack, dependencias, restricciones
- Ratificar DBML — Convertir campos
@provisionala ratificados - Generar contratos API, modelos, arquitectura de servicios
- Registrar Complejidad — Justificar desviaciones de simplicidad
- Crear archivo
.plan.mdenspecs/features/<dominio>/
Output
Genera specs/features/<dominio>/<Feature>.plan.md:
# Blueprint Técnico: CrearUsuario
**Rama:** feature/crear-usuario
**Spec:** specs/features/usuario/CrearUsuario.feature
**Fecha:** 2026-03-21
**Estado:** Borrador
---
## Resumen
Implementar registro de usuarios con email/contraseña, incluyendo
validación, hashing de contraseña y generación de JWT.
Enfoque técnico: API REST con patrón Controller → Service → Repository.
---
## Chequeo de Constitución
Verificación obligatoria contra `reglas/constitucion.md`:
| Artículo | Principio | Estado | Notas |
|----------|-----------|--------|-------|
| I | Gherkin es Rey | ✅ | Spec @lista aprobada |
| I-B | Schema como Verdad Viva | ✅ | DBML ratificado |
| II | Precisión Quirúrgica | ✅ | Cambio mínimo, 1 feature |
| III | Arquitectura Plug-and-Play | ✅ | Nuevo módulo, no infla existentes |
| IV | Regla Las Vegas | ✅ | Tests herméticos planificados |
| IV-B | Punto de Entrada | ✅ | Validación en Controller |
| V | Estándares Modernos | ✅ | Type hints + Pydantic/Zod |
| VI | Adaptabilidad | ✅ | Stack detectado: FastAPI |
| VII | Codificación Defensiva | ✅ | Excepciones custom planificadas |
**Resultado: ✅ PASA** — El plan es compatible con la constitución.
---
## Contexto Técnico
| Aspecto | Valor |
|---------|-------|
| **Lenguaje** | Python 3.12 / TypeScript 5.x |
| **Framework** | FastAPI 0.115 / Next.js 15 |
| **Dependencias** | bcryptjs, python-jose, pydantic |
| **Almacenamiento** | PostgreSQL 16 + Prisma/SQLAlchemy |
| **Testing** | pytest + pytest-asyncio / vitest |
| **Plataforma** | Docker + Linux |
| **Rendimiento** | < 500ms p95 (de criterios de éxito) |
| **Escala** | ~1,000 registros/día (estimado) |
| **Restricciones** | Sin OAuth en v1 (definido en clarificación) |
---
## Contrato API
POST /api/v1/usuarios
Content-Type: application/json
Request:
{
"email": "string (required, email format)",
"password": "string (required, min 8 chars)",
"nombre": "string (required, max 100 chars)"
}
Response 201:
{
"id": "uuid",
"email": "string",
"nombre": "string",
"token": "jwt-string",
"createdAt": "datetime"
}
Response 400:
{
"error": "string",
"field": "string (optional)"
}
Response 409:
{
"error": "El email ya está registrado"
}
---
## Modelo de Datos
Usuario (ratificado desde DBML):
- id: UUID (PK, auto-gen)
- email: String (unique, indexed, NOT NULL)
- password_hash: String (NOT NULL)
- nombre: String (max 100, NOT NULL)
- created_at: DateTime (default: now())
---
## Arquitectura de Servicios
Controller → Service → Repository → Database
↓
EmailService (async)
---
## Dependencias
- bcryptjs (hash de contraseña)
- python-jose / jsonwebtoken (generación JWT)
- pydantic / zod (validación de DTOs)
---
## Tracking de Complejidad
Justificar cualquier decisión que añade complejidad por encima de la alternativa más simple:
| Decisión | Alternativa Simple | Por Qué Se Rechazó |
|----------|--------------------|---------------------|
| JWT con refresh token | Solo JWT simple | Requerimiento de seguridad: tokens de corta duración |
| Email async con cola | Email síncrono | Bloquea respuesta al usuario, riesgo de timeout |
| Repository pattern | Queries directas | Testabilidad: inyección de dependencias para mocks |
Si la tabla está vacía, no hay desviaciones de simplicidad.
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.
- 7d ago First seen · 187 lines · 11 tokens per session scan A ab4c427af4ac
planificar-tecnico is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,463 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other commands, from other repositories
add-phase
Add phase to end of current milestone in roadmap.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead).
reapply-patches
Reapply local modifications after a PBR update.
add-todo
Capture idea or task as todo from current conversation context.
audit-milestone
Audit milestone completion against original intent before archiving.