dbv-specs-ops: Command for Claude Code

.claude/commands/build.md

build is a command for Claude Code from davidbuenov/dbv-specs-ops. It costs 18 tokens per session (1,105 once invoked), scanned A, original, MIT.

An implementation command for the Build stage of an SDD workflow. It checks for an approved plan and then develops the code incrementally, one small slice at a time.

In plain words
What is it for?
Use it to implement planned work incrementally while following the project's coding rules and file-header requirements.
Why use it?
It keeps coding connected to a reviewed specification and task plan. If those are missing, it prepares the earlier stages before implementation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is davidbuenov/dbv-specs-ops's own configuration. It tells Claude Code how to work on dbv-specs-ops itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dbv-specs-ops configures →

Reuse

Borrowing it

Nothing to install: this file belongs to davidbuenov/dbv-specs-ops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/davidbuenov/dbv-specs-ops/master/.claude/commands/build.md
Clone the repo
git clone --depth 1 https://github.com/davidbuenov/dbv-specs-ops

Made for: Claude Code.

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 build

README.md
[![agentmods](https://agentmods.dev/badge/commands/davidbuenov/dbv-specs-ops/build/github.svg)](https://agentmods.dev/commands/davidbuenov/dbv-specs-ops/build)
Your own site
<a href="https://agentmods.dev/commands/davidbuenov/dbv-specs-ops/build"><img src="https://agentmods.dev/badge/commands/davidbuenov/dbv-specs-ops/build/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 build

Your own site · 80×15
<a href="https://agentmods.dev/commands/davidbuenov/dbv-specs-ops/build"><img src="https://agentmods.dev/badge/commands/davidbuenov/dbv-specs-ops/build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,105 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 $0.00018 $0.01105
Opus 5.5 $0.00007 $0.00442
Sonnet 5.5 $0.00004 $0.00221
Haiku 4.5 $0.00002 $0.00111

Measured 4d ago against content hash f0260f628287, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build 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 4d 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.

.claude/commands/build.md · 47 lines

What it actually says

Ejecuta ahora la fase Build (/build) del ciclo Spec→Plan→Build→Test→Simplify→Ship definido en dbv-specs-ops/docs/MASTER_PROMPT.md (<workflow>, paso 3).

Antes de escribir código: si no existe un plan aprobado (dbv-specs-ops/task.md con pasos, o dbv-specs-ops/implementation_plan.md para tareas complejas), no rechaces la petición — ejecuta primero, en la misma respuesta, las fases previas que falten (Spec → Plan) siguiendo <specs_check> del MASTER_PROMPT.md, y continúa con el Build en cuanto estén resueltas.

Implementa de forma incremental ("one slice at a time"), siguiendo las normas de codificación y cabeceras de fichero del MASTER_PROMPT.md. Etiqueta con @spec REQ-NN el código que implemente un requisito con ID.

🕸️ Grafo de fases — nodo activo: Build

Fase 3: implementación incremental, una porción cada vez, con cabeceras y etiquetas @spec.

Al entrar — la transición por la que llegas fija la condición, cómo ejecutar esta fase y qué evitar:

  • desde Plan (PROVIDES_INPUT_FOR) — si: El plan ha superado el Architect Review y el usuario lo ha aprobado explícitamente.
    • Cómo: Implementa una porción cada vez. Cabecera de project.config.md en cada fichero nuevo, @spec REQ-NN en las funciones que implementan un requisito y entrada en CHANGELOG.md [Sin publicar]. Si contradices ARCHITECTURE.md, regístralo ya en memory.md.
    • Evita: Varios return fuera de las Guard Clauses iniciales (un solo return final); excepciones o None donde toca el patrón Result; any en TypeScript; .unwrap()/.expect() en comandos IPC de Rust; todo el React en App.tsx; en Tauri sin bundler, ES modules o una constante isTauri (usa IIFE y runningInTauri).
  • desde Test (TRIGGERS) — si: Algún test o Eval falla.
    • Cómo: Corrige la causa en el código y anótalo como Fixed en CHANGELOG.md. Si el fallo desmiente un supuesto de SPECIFICATIONS.md, regístralo en Lecciones Aprendidas de memory.md.
    • Evita: No relajes ni borres una aserción para poner el test en verde. No repitas un arreglo que ya se revirtió (míralo en la Rejection Memory).
  • desde Simplify (TRIGGERS) — si: La revisión deja un hallazgo Crítico que exige cambiar el comportamiento del código, o un refactor rompe los tests.
    • Cómo: Vuelve a Build solo para ese hallazgo y repasa Test antes de regresar a Simplify.
    • Evita: No mezcles la corrección con funcionalidad nueva. No ocultes el hallazgo rebajando su severidad.

Salidas (salto 1) — a dónde puedes ir y con qué condición:

  • Build → Test (LEADS_TO) — si: La porción está implementada, compila o se ejecuta sin errores y está anotada en CHANGELOG.md.
    • Cómo: Escribe y ejecuta tests deterministas que citen @spec REQ-NN para cada requisito tocado. Con componentes de IA, añade Evals; con un Agent Plugin, valida plugin.json y mcp.json.
    • Evita: No marques una tarea como hecha sin un test en verde. Si un enfoque falla y lo reviertes, regístralo en la Rejection Memory antes de probar otro.

Horizonte (salto 2) — lo que vendrá después y revisará tu trabajo:

  • Test ↩ Build (TRIGGERS) — si: Algún test o Eval falla.
  • Test → Simplify (PROVIDES_INPUT_FOR) — si: Todos los tests y Evals pasan, y ningún requisito con ID de la tarea se queda sin test.
    • Cómo: Haz los tres pases de docs/REVIEW.md (Bugs, Seguridad, Cumplimiento con <coding_standards>) y, si hay Python, ejecuta dbv-lint.py --changed. Después refactoriza para dar claridad sin cambiar el comportamiento.
    • Evita: No añadas funcionalidad nueva. Si un refactor rompe tests y lo reviertes, regístralo en la Rejection Memory.

Rutas relativas a dbv-specs-ops/. Lee la 🚫 Rejection Memory de memory.md antes de proponer un enfoque: lo que ya se descartó no se vuelve a proponer sin explicar qué ha cambiado.

$ARGUMENTS

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. 4d ago Changed · +30 lines f0260f628287
  2. 8d ago Changed · +1 lines c245ef5b9efe
  3. 1mo ago First seen · 16 lines · 18 tokens per session scan A fda861f8c35a

Subscribe to this mod's changes

build is a command published in the GitHub repository davidbuenov/dbv-specs-ops (29 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 1,105 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.