voicemode: Skill for Claude Code

.claude/skills/voicemode-connect/SKILL.md

voicemode-connect is a skill for Claude Code from mbailey/voicemode. It costs 37 tokens per session (585 once invoked), scanned B, original, MIT.

A connection service for two-way voice conversations between Claude Code and a phone or web app through VoiceMode Connect.

In plain words
What is it for?
Use it to check connected devices and start voice conversations through the VoiceMode Connect iOS app or web dashboard.
Why use it?
It lets users speak with the assistant without setting up speech-to-text and text-to-speech services on their own computer.

Skill for Claude Code

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

This is mbailey/voicemode's own configuration. It tells Claude Code how to work on voicemode 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 voicemode configures →

Part of the voicemode plugin — 5 skills, 3 commands, 1 agent, 5 hooks, 1 MCP server shipped together

About the project

VoiceMode adds natural spoken conversations to Claude Code and other agents that support MCP. Developers use it when their hands or eyes are busy, with optional local speech services for offline or privacy-focused use, and the catalogue provides skills, hooks, commands, plugins, instructions, agents, settings, and MCP integration for the workflow.

mbailey/voicemode · 1,350 stars · on GitHub · voicemode.dev

Reuse

Borrowing it

Nothing to install: this file belongs to mbailey/voicemode. 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/mbailey/voicemode/master/.claude/skills/voicemode-connect/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mbailey/voicemode

Made for: Claude Code.

Or install voicemode, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 1 agent, 5 hooks, 1 MCP server.

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 voicemode-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/mbailey/voicemode/voicemode-connect.svg)](https://agentmods.dev/skills/mbailey/voicemode/voicemode-connect)
Your own site
<a href="https://agentmods.dev/skills/mbailey/voicemode/voicemode-connect"><img src="https://agentmods.dev/badge/skills/mbailey/voicemode/voicemode-connect.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 20
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
How audits are shown
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 $0.00037 $0.00585
Opus 5 $0.00018 $0.00293
Sonnet 5 $0.00007 $0.00117
Haiku 4.5 $0.00004 $0.00059

Measured 8d ago against content hash a467939b3b3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

voicemode-connect scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Add to your Claude Code MCP settings (`~/.claude/settings.json`):
.claude/skills/voicemode-connect/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VoiceMode Connect

Voice conversations through the voicemode.dev cloud platform. Connect your AI assistant to voice clients (iOS app, web app) without running local STT/TTS services.

How It Works

Agents (Claude Code, claude.ai) connect via MCP to voicemode.dev. Clients (iOS app, web app) connect via WebSocket. The platform routes voice messages between them.

Quick Setup

1. Add the MCP Server

Add to your Claude Code MCP settings (~/.claude/settings.json):

{
  "mcpServers": {
    "voicemode-dev": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://voicemode.dev/mcp"]
    }
  }
}

2. Authenticate

When you first use a Connect tool, Claude Code will prompt for OAuth authentication. Sign in with your voicemode.dev account.

3. Connect a Client

Open the iOS app or web dashboard (voicemode.dev/dashboard) and sign in with the same account.

4. Start Talking

Use the status tool to see connected devices, then use converse to have a voice conversation.

MCP Tools

Tool Description
status Show connected devices and agents
converse Two-way voice conversation via connected client

Relationship to Local VoiceMode

Feature Local VoiceMode VoiceMode Connect
STT/TTS Local (Whisper/Kokoro) Client device (phone/browser)
Setup Install services Just add MCP server
Internet Optional Required
Latency Lower Higher
Mobile voice No Yes

Use both: Local VoiceMode for desktop voice, Connect for mobile voice.

Documentation

Open Questions

  • How do multiple agents on the same account interact?
  • What happens when multiple clients are connected?
  • How is the target device selected for converse?

Read the full file on GitHub · 78 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. 8d ago First seen · 78 lines · 37 tokens per session scan B a467939b3b3d

Subscribe to this mod's changes

voicemode-connect is a skill published in the GitHub repository mbailey/voicemode (1,350 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 585 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

post-to-xhs

A publishing guide for 小红书, a Chinese social-media platform. It covers posting image-and-text content or a longer formatted article, using supplied content or a webpage.

xpzouying/xiaohongshu-mcp · 96 tokens

screenshot-game-view

Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.

IvanMurzak/Unity-MCP · 58 tokens

screenshot-scene-view

Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera onto a temporary RenderTexture. Requires an open Scene View.

IvanMurzak/Unity-MCP · 42 tokens

create-video-seedance-2-fal

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…

gooseworks-ai/goose-skills · 117 tokens

create-workflow-diagram

Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.

gooseworks-ai/goose-skills · 45 tokens

demo-builder

Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK. Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link.

gooseworks-ai/goose-skills · 46 tokens