vox: Instructions file for Claude Code

CLAUDE.md

vox CLAUDE.md is an instructions file for Claude Code from punt-labs/vox. It costs 7,362 tokens per session, scanned A, original, MIT.

Repository instructions and architecture notes for Vox, a text-to-speech command-line tool, MCP server, and Claude Code plugin. They explain its required workspace setup, coding rules, and separation between the background service and its clients.

In plain words
What is it for?
Use them when working on Vox, its synthesis system, Python code, CLI, MCP server, or Claude Code integration. They also guide setup and incremental code-quality improvements.
Why use it?
They give the coding agent the project rules and dependencies it must know before changing Vox. This helps avoid missing organization-wide configuration or crossing the daemon–client boundary.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

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

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

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

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/punt-labs/vox/claude-md.svg)](https://agentmods.dev/instructions/punt-labs/vox/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/punt-labs/vox/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/vox/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,362 This file is loaded in full into every session.
When invoked 7,362 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.07362 $0.07362
Opus 5 $0.03681 $0.03681
Sonnet 5 $0.01472 $0.01472
Haiku 4.5 $0.00736 $0.00736

Measured 6d ago against content hash a8fb6ad361cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vox CLAUDE.md 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 6d 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.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vox

Part of Punt Labs. This repo must be checked out inside the punt-labs/ workspace meta-repo so that org-wide configuration loads via Claude Code's ancestor directory walk:

  • punt-labs/CLAUDE.md — org workflow, delegation model, beads issue tracking, tool configuration
  • punt-labs/.claude/rules/python-*.md — 19 Python OO coding rules, scoped via paths: frontmatter (load on-demand when .py files are touched)
  • punt-labs/.envrc — git identity, beads DB connection, API keys from platform keychain
  • punt-kit/standards/ — canonical reference docs

If cloned outside the workspace, these rules and configuration will not be present.

OO Python standards adopted 2026-05-13. The codebase does not yet fully comply. Every commit must improve OO scores (make check-oo), never regress. Do not match existing code patterns that violate the rules — write new code to the standard and improve touched files incrementally.

Text-to-speech CLI, MCP server, and Claude Code plugin. Supports ElevenLabs (premium), AWS Polly, and OpenAI TTS.

  • Package: punt-vox
  • CLI: vox
  • MCP server: vox-server
  • Python: 3.13+, managed with uv

Mandatory Reading

Source-of-truth documents, @-imported so they load into context at session start. Read them before writing code.

@docs/WORKFLOW.md @../punt-kit/standards/architecture.md @../punt-kit/standards/oo.md @../punt-kit/standards/python.md

WORKFLOW.md is the three-loop development process (backlog → PR → mission), with pseudocode and an entry/exit Z schema at each level. The punt-kit/standards imports are the org's canonical engine-and-clients architecture, object-oriented stance, and Python standard (including the OO ratchet vox already runs) — cross-repo (external) imports, so the first load may ask for approval.

Architecture

How synthesis works

An agent (or human) calls an MCP tool or CLI command requesting speech. The request flows through the thin client layer (client.py → WebSocket → voxd). The daemon selects a provider (ElevenLabs > OpenAI > Polly > platform fallback), synthesizes audio, optionally caches the result (content-addressed by text+voice+provider via MD5), and plays it through the system audio stack (afplay on macOS, ffplay on Linux). Long texts are split by core.py into sentence-boundary chunks and synthesized in parallel.

Read the full file on GitHub · 274 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. 6d ago First seen · 274 lines · 7,362 tokens per session scan A a8fb6ad361cd

Subscribe to this mod's changes

vox CLAUDE.md is an instructions file published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 7,362 tokens to every session, about $0.0368 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 2026-08-31.

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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens