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/doncheli/don-cheli-sdd/comenzargit 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/comenzar)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/comenzar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/comenzar.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 5.1 | $0.00102 | $0.01597 |
| Opus 5 | $0.00051 | $0.00798 |
| Sonnet 5 | $0.00020 | $0.00319 |
| Haiku 4.5 | $0.00010 | $0.00160 |
Grade A, and why
comenzar 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:comenzar
Objetivo
Iniciar una tarea detectando automáticamente el nivel de complejidad (0-4) y ejecutando el flujo apropiado.
Uso
/dc:comenzar <descripción de la tarea>
Auto-Detección de Nivel
Evaluar cada dimensión de 0 a 4:
Alcance: 0=1 archivo 1=2-3 archivos 2=módulo 3=multi-módulo 4=sistema
Incógnitas: 0=ninguna 1=menores 2=algunas 3=significativas 4=fundamentales
Riesgo: 0=trivial 1=bajo 2=medio 3=alto 4=crítico
Duración: 0=<30min 1=horas 2=días 3=1-2 semanas 4=semanas+
Nivel = max(puntuaciones) // Conservador: gana la dimensión más alta
Niveles
| Nivel | Nombre | Proceso |
|---|---|---|
| 0 | Atómico | Ejecutar directamente |
| P | PoC | Hipótesis → Construir → Evaluar → Veredicto |
| 1 | Micro | Planear → Ejecutar → Verificar |
| 2 | Estándar | 5 fases (sin Descubrimiento/Crecimiento) |
| 3 | Complejo | 7 fases completas |
| 4 | Producto | 7 fases + artefactos completos |
Detección de PoC: Si la tarea es una pregunta ("¿se puede...?", "¿funciona...?", "¿vale la pena...?") o incluye palabras como "probar", "viabilidad", "validar", "explorar opción" → sugerir /dc:poc.
Comportamiento
- Detectar PRD — ¿Existe
.dc/prd/prd-*.md? ¿El usuario proporcionó brief, Figma o docs?- Si hay PRD existente → usarlo como input para las fases siguientes
- Si hay brief/Figma/docs pero no PRD → preguntar: "¿Quieres generar un PRD primero? (/dc:prd)"
- Si no hay nada → continuar sin PRD (flujo normal)
- Analizar la descripción de la tarea (o el PRD si existe)
- Evaluar las 4 dimensiones (alcance, incógnitas, riesgo, duración)
- Determinar nivel de complejidad
- Mostrar evaluación al usuario
- Preguntar si está de acuerdo o desea ajustar
- Iniciar flujo del nivel correspondiente
Flujo con PRD (niveles 2-4)
¿Se detectó PRD o fuentes de producto?
│
├─ SÍ, PRD existe (.dc/prd/prd-*.md)
│ → Leer PRD
│ → Extraer user stories, prioridades, riesgos
│ → Alimentar /dc:especificar automáticamente
│
├─ SÍ, hay brief/Figma pero no PRD
│ → "Se detectaron fuentes de producto. ¿Generar PRD? (s/n)"
│ → Si sí: /dc:prd → luego continúa el pipeline
│ → Si no: continuar sin PRD
│
└─ NO hay fuentes de producto
→ Flujo normal (el usuario describe la tarea)
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 First seen · 131 lines · 102 tokens per session scan A 01af8cec972d
comenzar is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 26d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,597 once invoked, about $0.0005 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.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
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.
join-discord
Join the PBR Discord community.