especificar

especificar is a command for Claude Code from doncheli/don-cheli-sdd. It costs 90 tokens per session (2,246 once invoked), scanned A, original, Apache-2.0.

A requirements-to-specification command that turns natural-language requirements into Gherkin feature files, with related database and API schemas when applicable. Gherkin is a plain-text format for describing expected software behavior.

In plain words
What is it for?
Use it to define commands, queries, or events, document features, and generate Gherkin, DBML database schemas, OpenAPI API descriptions, or JSON Schemas.
Why use it?
It creates a structured, testable source of truth before implementation and can derive supporting technical documents from it.

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 Use it to define commands, queries, or events, document features, and generate Gherkin, DBML database schemas, OpenAPI API descriptions, or JSON Schemas.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/especificar/github.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/especificar)
Your own site
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/especificar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/especificar/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 especificar

Your own site · 80×15
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/especificar"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/especificar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,246 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 $0.00090 $0.02246
Opus 5 $0.00045 $0.01123
Sonnet 5 $0.00018 $0.00449
Haiku 4.5 $0.00009 $0.00225

Measured 6d ago against content hash 7e7165b1151d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

especificar 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 6d 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/especificar.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dc:especificar

Objetivo

Convertir un requerimiento en lenguaje natural a una especificación Gherkin estructurada (.feature), la fuente de verdad principal de Don Cheli.

Output principal (siempre):

  1. Gherkin (.feature) — Comportamiento verificable con escenarios P1/P2/P3+
  2. DBML — Schema de base de datos provisional o ratificado

Output opcional (auto-generado si se detectan endpoints HTTP): 3. OpenAPI 3.1 (openapi.yaml) — Contratos de API extraídos desde los escenarios Gherkin 4. JSON Schema (schemas/*.json) — Estructura de datos derivada del DBML

Mejorado con el ciclo de vida DBML de Specular (constitution.md §I-B) Alineado con spec-kit — prioridades P1/P2/P3+, criterios de éxito y marcadores de clarificación Gherkin es Rey — OpenAPI y JSON Schema son complementos opcionales que se derivan del Gherkin, nunca al revés

Uso

/dc:especificar Tipo: <COMANDO|CONSULTA|EVENTO> Feature: <dominio/Nombre> Dominio: <dominio> Requerimiento: <descripción> Contexto: @<archivo-referencia>

Comportamiento

  1. Detectar PRD — Si existe .dc/prd/prd-*.md:

    • Leer el PRD y extraer automáticamente:
      • User stories (sección 6.1) → base para escenarios Gherkin
      • Prioridades MoSCoW → mapear a P1 (Must), P2 (Should), P3+ (Could/Won't)
      • Riesgos (sección 8) → agregar escenarios de error/edge case por riesgo
      • Requirements no funcionales (sección 6.2) → anotar como constraints
      • Data model DBML (sección 6.4) → usar como schema base si existe
    • Informar al usuario: "PRD detectado — extrayendo X user stories, Y riesgos"
    • Si no hay PRD → continuar con el flujo normal (input del usuario)
  2. Verificar si existe specs/db_schema/<dominio>.dbml

    • Si NO existe → Auto-generar DBML @provisional con campos inferidos del requerimiento
    • Si existe y está ratificado → Usar como referencia, agregar nuevos campos como @provisional
  3. Analizar el requerimiento proporcionado

  4. Identificar actores, acciones y resultados esperados

  5. Categorizar escenarios por prioridad (P1/P2/P3+)

  6. Generar escenarios Gherkin con Dado/Cuando/Entonces

  7. Usar los nombres de campo EXACTOS del DBML en los escenarios

  8. Marcar requisitos ambiguos con [NECESITA CLARIFICACIÓN]

  9. Definir criterios de éxito medibles y agnósticos de tecnología

  10. Crear archivo .feature en specs/features/<dominio>/ con tag @borrador

  11. Incluir edge cases y escenarios de error

  12. Generar checklist de requisitos vacía (requisitos.md)

Read the full file on GitHub · 209 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. 6d ago First seen · 209 lines · 90 tokens per session scan A 7e7165b1151d

Subscribe to this mod's changes

especificar is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 90 tokens to every session and 2,246 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.