A specification review command that finds unclear requirements, missing edge cases, and mismatches between Gherkin scenarios and a database schema. Gherkin is a plain-language format for describing software behaviour.

Use it to ask focused clarification questions, record answers in a feature file, and check that referenced database fields match the DBML schema.

It exposes gaps and inconsistencies before implementation or testing begins.

clarificar — Command for Claude Code by doncheli

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/clarificar/github.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/clarificar)

Your own site

<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/clarificar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/clarificar/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/clarificar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/clarificar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 821 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.00821
Opus 5	$0.00010	$0.00411
Sonnet 5	$0.00004	$0.00164
Haiku 4.5	$0.00002	$0.00082

Measured 5d ago against content hash a5f5534b79a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

clarificar 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/clarificar.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dc:clarificar

Objetivo

Analizar una especificación Gherkin actuando como Ingeniero QA Estricto: detectar ambigüedades, ejecutar verificaciones automáticas de consistencia Schema↔Spec, y registrar las respuestas en el archivo .feature.

Mejorado con el protocolo Auto-QA de Specular (constitution.md §VIII)

Uso

/dc:clarificar @specs/features/<dominio>/<Feature>.feature

Comportamiento

Fase 1: Análisis de Ambigüedades (Original)

Leer el archivo .feature
Analizar cada escenario buscando:
- Términos ambiguos o no definidos
- Casos límite no cubiertos
- Validaciones implícitas
- Dependencias no mencionadas
Formular hasta 5 preguntas dirigidas
Registrar las respuestas en el archivo .feature como comentarios

Fase 2: Verificación Auto-QA (De Specular)

Ejecutar automáticamente SIN pedir instrucciones adicionales:

2.1 Verificación de Consistencia Schema-Spec (DBML)

Escanear todos los campos mencionados en el Gherkin
Comparar contra el schema DBML en specs/db_schema/<dominio>.dbml
❌ Error si nombres de campos no coinciden exactamente (ej: user_id vs userId)
❌ Error si un campo NOT NULL en DBML no tiene escenario de validación en Gherkin

2.2 Verificación de Convención de Nombres

Feature COMMAND: Usar patrón de precondición + postcondición
Feature QUERY: Usar patrón de precondición + éxito

2.3 Auditoría de Escenarios Auto-Generados

Revisar escenarios tagueados @auto_generado
Marcar los que sean redundantes o lógicamente imposibles

Fase 3: Generar Checklist de Requisitos

Generar automáticamente requisitos.md con evidencia citada para cada item.

Output

=== Reporte Auto-QA ===

Feature: CrearUsuario.feature

## Ambigüedades Detectadas: 3
1. ¿Qué longitud mínima/máxima debe tener la contraseña?
2. ¿Se permite registro con proveedores OAuth (Google, GitHub)?
3. ¿El email de bienvenida es síncrono o asíncrono?

## Verificación Schema-Spec
✅ PASS: Campo "email" coincide con usuario.dbml
✅ PASS: Campo "password_hash" tiene escenario de validación
❌ FAIL: Campo "nombre" en DBML es NOT NULL pero no tiene escenario de validación

## Verificación de Convenciones
✅ PASS: Feature COMMAND usa patrón precondición/postcondición
⚠️ WARNING: Escenario "Contraseña débil" no verifica postcondición

## Auditoría Auto-Generado
✅ PASS: Sin escenarios redundantes

## Resultado
NO-AVANZAR (1 FAIL)
→ Acción requerida: Agregar escenario de validación para campo "nombre"

Read the full file on GitHub · 99 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.

5d ago First seen · 99 lines · 19 tokens per session scan A a5f5534b79a5

Subscribe to this mod's changes

clarificar is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 19 tokens to every session and 821 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.

Databases Testing agentic-coding ai-agents ai-coding ai-development anthropic-skills claude

clarificar