desglosar

desglosar is a command for Claude Code from doncheli/don-cheli-sdd. It costs 22 tokens per session (1,590 once invoked), scanned A, original, Apache-2.0.

A command that turns a technical blueprint into an ordered task list, using TDD (writing a failing test, making it pass, then improving the code) and marking tasks that can run in parallel.

In plain words
What is it for?
Breaking features into numbered implementation tasks, organising work into phases, and identifying tasks that can be done at the same time.
Why use it?
It removes the need to manually turn a design into an execution plan and makes dependencies between tasks clearer.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the don-cheli-sdd plugin — 28 skills, 115 commands, 1 agent shipped together

Good fit Breaking features into numbered implementation tasks, organising work into phases, and identifying tasks that can be done at the same time.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/doncheli/don-cheli-sdd/desglosar
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.

Clone the repo
git clone --depth 1 https://github.com/doncheli/don-cheli-sdd

Made for: Claude Code.

Or install don-cheli-sdd, the plugin that ships this one along with the rest of its 28 skills, 115 commands, 1 agent.

Wrote 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.

agentmods badge for desglosar

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/desglosar/github.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/desglosar)
Your own site
<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.

agentmods 80×15 button for desglosar

Your own site · 80×15
<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>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00022 $0.01590
Opus 5 $0.00011 $0.00795
Sonnet 5 $0.00004 $0.00318
Haiku 4.5 $0.00002 $0.00159

Measured 5d ago against content hash 7128b6ffcdb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

scripts/.claude/commands/dc/desglosar.md · 173 lines

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] Descripción y 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

Read the full file on GitHub · 173 lines

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. 5d ago First seen · 173 lines · 22 tokens per session scan A 7128b6ffcdb2

Subscribe to this mod's changes

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.