voice

A voice-input setup and management tool for Claude Code on macOS. It connects a microphone to speech-to-text, which turns spoken words into written commands, and can paste the result into a session.

In plain words
What is it for?
It helps install and test voice input, download the Whisper speech-recognition model, configure Hammerspoon, check the setup, diagnose problems, and uninstall it.
Why use it?
It removes the need to type every command and provides checks for missing dependencies, model setup, connection status, and troubleshooting.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ggombee/code-forge/voice
Any agent
npx skills add ggombee/code-forge --skill voice
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,854 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00074 $0.01854
Opus 5 $0.00037 $0.00927
Sonnet 5 $0.00015 $0.00371
Haiku 4.5 $0.00007 $0.00185

Measured 2d ago against content hash a6f74dd7e127, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

voice scanned grade C with 2 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.local/share/forge-voice

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL -o ~/.whisper/models/ggml-small.bin \
skills/voice/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/voice — Forge Voice 셋업 & 관리

code-forge의 음성 입력 확장. 대장간 비유: Anvil(작업대)에 명령을 외치면 → Forge Voice가 받아 → Smith/Implementor가 단조.


서브커맨드

사용 동작
/voice 또는 /voice setup 1회 셋업 (의존성 + 모델 + Hammerspoon 설정)
/voice test 동작 검증 (마이크 → STT → paste 풀 회로)
/voice status 현재 상태 (의존성 / 모델 / hook 활성)
/voice doctor 트러블슈팅 진단
/voice uninstall 셋업 되돌리기

/voice setup — 1회 셋업

다음을 순서대로 실행 (사용자 확인 받으면서):

1. 의존성 점검

for cmd in sox whisper-cpp jq; do
  command -v "$cmd" >/dev/null 2>&1 || echo "  ❌ $cmd 없음"
done
command -v cliclick >/dev/null 2>&1 || echo "  ⚠️ cliclick 없음 (옵션, 자동 paste 정확도 ↑)"
brew list --cask hammerspoon >/dev/null 2>&1 || echo "  ❌ Hammerspoon 없음"

누락 시 사용자에게 한 줄 install 안내:

brew install whisper-cpp sox jq cliclick
brew install --cask hammerspoon

2. Whisper 모델 다운로드

~/.whisper/models/ggml-small.bin 없으면:

mkdir -p ~/.whisper/models
curl -fsSL -o ~/.whisper/models/ggml-small.bin \
  https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin

→ 244MB, 한국어 OK. medium 모델은 사용자에게 옵션 제안 (1.5GB, 정확도 ↑↑).

3. forge-voice 스크립트 + Lua 설치

mkdir -p ~/.local/bin ~/.local/share/forge-voice ~/.hammerspoon

PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(claude plugin path code-forge)}"

cp "$PLUGIN_ROOT/tools/forge-voice.sh" ~/.local/bin/forge-voice.sh
chmod +x ~/.local/bin/forge-voice.sh

cp "$PLUGIN_ROOT/tools/forge-voice.lua" ~/.local/share/forge-voice/forge-voice.lua

4. Hammerspoon init.lua 등록

~/.hammerspoon/init.lua에 1줄 (중복 안 들어가게 grep 체크):

LINE='dofile(os.getenv("HOME") .. "/.local/share/forge-voice/forge-voice.lua")'
if ! grep -qF "forge-voice.lua" ~/.hammerspoon/init.lua 2>/dev/null; then
  echo "$LINE" >> ~/.hammerspoon/init.lua
fi

→ Hammerspoon 메뉴바 → Reload Config 안내.

5. macOS 권한 안내

사용자에게 직접 허용해야 하는 항목:

  • 시스템 환경설정 → 보안 → 마이크: Hammerspoon 허용
  • 시스템 환경설정 → 보안 → 접근성: Hammerspoon 허용 (cliclick 사용 시)

→ 본 단계는 시스템 권한이라 자동화 불가. 사용자 직접 수행 후 /voice test.

Read the full file on GitHub · 184 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. 2d ago First seen · 184 lines · 74 tokens per session scan C a6f74dd7e127

Subscribe to this mod's changes

voice is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,854 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens