voice

voice is a command for Claude Code from doncheli/don-cheli-sdd. It costs 78 tokens per session (607 once invoked), scanned A, original, Apache-2.0.

A voice-input command for turning spoken ideas, requirements, or review comments into structured text. It can format specifications as Gherkin, a plain-language style for describing software behavior with given conditions, actions, and results.

In plain words
What is it for?
Use it to dictate a specification, code review, or brainstorming session, then clean up the transcription and organize the result.
Why use it?
It reduces the effort of writing while preserving a structured format for specifications, reviews, and brainstorming.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

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

Good fit Use it to dictate a specification, code review, or brainstorming session, then…

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/voice.svg)](https://agentmods.dev/commands/doncheli/don-cheli-sdd/voice)
Your own site
<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/voice"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 607 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 $0.00078 $0.00607
Opus 5 $0.00039 $0.00303
Sonnet 5 $0.00016 $0.00121
Haiku 4.5 $0.00008 $0.00061

Measured 3d ago against content hash aa0274fd579d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

voice 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 3d 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/voice.md · 63 lines

What it actually says

/dc:voice

Objetivo

Capturar input de voz del usuario y convertirlo en specs estructuradas en formato Gherkin, notas de revisión o ideas de brainstorming. Reduce la fricción de escritura al permitir dictar en lenguaje natural y recibir output listo para el flujo SDD.

Uso

/dc:voice spec
/dc:voice review
/dc:voice brainstorm
/dc:voice --lang en

Comportamiento

  1. Detectar modo: spec, review o brainstorm (default: spec)
  2. Indicar al usuario que active Voice Mode en Claude Code (Ctrl+Shift+V o equivalente)
  3. Transcribir el input de voz recibido
  4. Limpiar muletillas, repeticiones y fragmentos incompletos
  5. Estructurar según el modo seleccionado:
    • spec → Gherkin (Feature / Scenario / Given-When-Then)
    • review → lista de comentarios numerados con severidad [blocker|suggestion|nitpick]
    • brainstorm → ideas en bullets organizados por tema
  6. Confirmar con el usuario antes de guardar en .dc/

Modos

Modo Input esperado Output
spec Descripción funcional en lenguaje natural Feature file .feature o bloque Gherkin
review Comentarios sobre código o spec Lista de revisión estructurada
brainstorm Ideas libres, lluvia de ideas Bullets agrupados por tema

Reglas de Transcripción

  • Preservar la intención, no las palabras exactas
  • Inferir el idioma configurado en .dc/config.yaml
  • Marcar con [inaudible] segmentos no interpretables
  • No inventar detalles que no se dictaron — preguntar si hay ambigüedad

Output

# Generado por /dc:voice — 2026-03-28
Feature: <nombre inferido del dictado>

  Scenario: <escenario 1>
    Given <precondición>
    When <acción>
    Then <resultado esperado>

  # [inaudible en 0:42 — revisar]

Para brainstorm y review, el output es Markdown en /tmp/voice-capture-<timestamp>.md con opción de mover a .dc/.

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. 3d ago First seen · 63 lines · 78 tokens per session scan A aa0274fd579d

Subscribe to this mod's changes

voice is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 27d ago), licensed Apache-2.0. It adds 78 tokens to every session and 607 once invoked, about $0.0004 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.