agentmods.dev

vox-machina: Instructions file for Claude Code

CLAUDE.md

vox-machina CLAUDE.md is an instructions file for Claude Code from darkcrux/vox-machina. It costs 668 tokens per session, scanned B, original, MIT.

A project instruction file for Claude Code, describing the vox-machina command-line tool, its structure, installation, audio packs, and configuration.

In plain words
What is it for?
Use it as a reference when working on the single-file CLI, installation script, voice-pack folders, configuration, or Claude Code hook events.
Why use it?
It gives Claude Code the project context needed to make changes that fit the existing Bash program and its hook-based audio behaviour.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is darkcrux/vox-machina's own configuration. It tells Claude Code how to work on vox-machina 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 vox-machina configures →

not rated 1repo 5mo ago B scan 668 tokens original MIT
View source ↗ darkcrux/vox-machina
Reuse

Borrowing it

Nothing to install: this file belongs to darkcrux/vox-machina. 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/darkcrux/vox-machina/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/darkcrux/vox-machina

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 vox-machina CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/darkcrux/vox-machina/claude-md/github.svg)](https://agentmods.dev/instructions/darkcrux/vox-machina/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/darkcrux/vox-machina/claude-md"><img src="https://agentmods.dev/badge/instructions/darkcrux/vox-machina/claude-md/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 vox-machina CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/darkcrux/vox-machina/claude-md"><img src="https://agentmods.dev/badge/instructions/darkcrux/vox-machina/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 668 This file is loaded in full into every session.
When invoked 668 The same file — it is already loaded in full.
Security scan B 2 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 $0.00668 $0.00668
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured 9d ago against content hash 4dfa974cb1ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

vox-machina CLAUDE.md scanned grade B 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 9d 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.

- **Hooks integration** — `cmd_hooks_install` injects `vox-machina play <event>` commands into `~/.claude/settings.json`.

Makes network callslowCapability

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

- No build step, no dependencies beyond bash/python3/curl/unzip and an audio player.
CLAUDE.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

vox-machina is a single-file Bash CLI (vox-machina.sh) that plays random audio clips in response to Claude Code hook events (SessionStart, Stop, Notification, PreToolUse, PostToolUse, PostToolUseFailure, SessionEnd, PreCompact). Users install themed "voice packs" (e.g., GLaDOS, Overmind, Wheatley) and the tool picks a random clip from the matching hook folder.

Architecture

  • vox-machina.sh — The entire CLI. All commands live here as cmd_* functions dispatched by a case block at the bottom. A single vox_helper() function wraps all Python logic in one heredoc; bash passes data via VOX_* environment variables (never interpolated into Python source).
  • install.sh — Downloads vox-machina.sh to ~/.vox-machina/ and symlinks to ~/.local/bin/vox-machina.
  • Voice packs — Directories of audio files organized as <voice>/<HookName>/*.{wav,aiff,mp3}. Distributed as zip files via GitHub Releases. Stored at ~/.vox-machina/voices/.
  • Config — ~/.vox-machina/config.json stores active_voice, muted, and volume state. Read/written via config_get/config_set helpers.
  • Hooks integration — cmd_hooks_install injects vox-machina play <event> commands into ~/.claude/settings.json.
  • Personality system — cmd_personality_install writes a voice-themed personality prompt into ~/.claude/CLAUDE.md (wrapped in HTML comment markers for clean replacement). Built-in personalities exist for GLaDOS, Wheatley, Overmind, and Gandalf. Voice packs can bundle a custom personality.md file.

Key Details

  • No build step, no dependencies beyond bash/python3/curl/unzip and an audio player.
  • Audio playback is platform-aware: afplay on macOS, cascading fallback (paplay > mpv > ffplay > aplay) on Linux. Volume control is supported where the player allows it.
  • TTS generation (cmd_generate) supports four engines: say (macOS), espeak (Linux), piper (Linux), glados (API).
  • Voice packs are gitignored — they're built separately and attached to GitHub Releases.
  • VOX_MACHINA_HOME env var overrides the default ~/.vox-machina location.

Read the full file on GitHub · 41 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. 9d ago First seen · 41 lines · 668 tokens per session scan B 4dfa974cb1ee

Subscribe to this mod's changes

vox-machina CLAUDE.md is an instructions file published in the GitHub repository darkcrux/vox-machina (1 stars, last pushed 5mo ago), licensed MIT. It adds 668 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Codeaudiobashclaude-code-hooksclideveloper-tools
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens