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/desglosar)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/desglosar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/desglosar/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/desglosar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/desglosar.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 | $0.00022 | $0.01590 |
| Opus 5 | $0.00011 | $0.00795 |
| Sonnet 5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
desglosar 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:desglosar
Objetivo
Convertir un blueprint técnico en una lista de tareas ordenadas con enfoque TDD (RED → GREEN → REFACTOR), marcadores de paralelismo [P] y fases de ejecución estandarizadas.
Alineado con spec-kit (github/spec-kit) — formato
[ID] [P?] [Story] Descripcióny 5 fases de ejecución
Uso
/dc:desglosar @specs/features/<dominio>/<Feature>.plan.md
Formato de Tareas
[TID] [P?] [Historia] Descripción
| Campo | Significado | Ejemplo |
|---|---|---|
TID |
ID único de tarea | T001 |
[P] |
Paralelizable (puede ejecutarse en paralelo con otras [P] de la misma fase) |
[P] o vacío |
[Historia] |
Historia de usuario asociada | [US1] |
| Descripción | Qué hacer | Crear modelo de Usuario |
Output
Genera specs/features/<dominio>/<Feature>.tasks.md:
# Tareas: CrearUsuario
**Feature:** usuario/CrearUsuario
**Plan:** specs/features/usuario/CrearUsuario.plan.md
**Creado:** 2026-03-21
## Formato: [TID] [P?] [Historia] Descripción
---
## Fase 1: Setup (Paralelizable)
Inicialización del entorno y estructura del proyecto.
- [T001] [P] Setup: Crear estructura de directorios del módulo usuario
- [T002] [P] Setup: Inicializar configuración de testing
- [T003] [P] Setup: Configurar Docker compose para tests
---
## Fase 2: Fundación (Secuencial después de Setup)
Infraestructura crítica que el resto del código necesita.
- [T004] [US1] RED: Escribir test para modelo Usuario
- [T005] [US1] GREEN: Implementar modelo Usuario con validaciones
- Archivos: `models/usuario.py`, `tests/unit/test_usuario.py`
- [T006] [US1] RED: Escribir test para UsuarioRepository (crear/buscar)
- [T007] [US1] GREEN: Implementar UsuarioRepository
- Archivos: `repositories/usuario_repo.py`, `tests/unit/test_usuario_repo.py`
---
## Fase 3: Historias de Usuario (Por prioridad)
### P1: Camino Crítico
- [T008] [US1] RED: Test para registro exitoso (happy path)
- [T009] [US1] RED: Test para email duplicado (sad path)
- [T010] [US1] GREEN: Implementar UsuarioService.crear()
- Archivos: `services/usuario_service.py`, `tests/unit/test_usuario_service.py`
- [T011] [P] [US1] RED: Test de integración para POST /usuarios
- [T012] [P] [US1] RED: Test BDD desde escenarios Gherkin P1
- [T013] [US1] GREEN: Implementar UsuarioController
- Archivos: `controllers/usuario_controller.py`, `tests/integration/test_crear_usuario.py`
### P2: Importante
- [T014] [US2] RED: Test para campo obligatorio vacío
- [T015] [US2] RED: Test para contraseña débil
- [T016] [US2] GREEN: Implementar validaciones adicionales
- [T017] [P] [US2] RED: Test BDD desde escenarios Gherkin P2
---
## Fase 4: Polish (Paralelizable)
Refinamientos transversales.
- [T018] [P] Refactor: Extraer validaciones a módulo compartido (si aplica)
- [T019] [P] Docs: Actualizar API docs con nuevo endpoint
- [T020] [P] Lint: Ejecutar linter y corregir warnings
---
## Fase 5: Verificación Final
- [T021] Ejecutar suite completa de tests
- [T022] Verificar coverage ≥ 85% sobre código nuevo
- [T023] Verificar lint y type-check sin errores
- [T024] Verificar build exitoso
---
## Orden de Ejecución
Fase 1: T001 ║ T002 ║ T003 (paralelo) ↓ Fase 2: T004 → T005 → T006 → T007 (secuencial) ↓ Fase 3: T008 → T009 → T010 → T011 ║ T012 → T013 (mixto) T014 → T015 → T016 → T017 (secuencial) ↓ Fase 4: T018 ║ T019 ║ T020 (paralelo) ↓ Fase 5: T021 → T022 → T023 → T024 (secuencial)
**Leyenda:** `→` secuencial | `║` paralelo
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 · 173 lines · 22 tokens per session scan A 7128b6ffcdb2
desglosar is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,590 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
review
Verify the build matched the plan. Automated checks + walkthrough with you.
test
Generate tests for completed phase code. Detects test framework and targets key files.
validate-phase
Post-build quality gate. Identifies test gaps and spawns nyquist-auditor to fill them.
verify-work
Validate built features through conversational UAT.
feature-implement-execute
Phase 4 of develop: Execute the implementation plan with per-task TDD, quality gates, and completion verification.
ccc-feature-start
Kickoff a new feature with branch creation, TDD setup, and task breakdown.