What is vibedungeon-voice CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, working on a voice server for a tabletop role-playing game that uses language models.

Setting up, running, testing, and modifying the server, especially its tools, voice-agent flows, and audio pipelines.

They explain the project's context, commands, environment needs, and architecture so code changes fit the game and its audio workflows.

How brandon-fryslie/vibedungeon-voice configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to brandon-fryslie/vibedungeon-voice. 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/brandon-fryslie/vibedungeon-voice/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/brandon-fryslie/vibedungeon-voice

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/brandon-fryslie/vibedungeon-voice/claude-md/github.svg)](https://agentmods.dev/instructions/brandon-fryslie/vibedungeon-voice/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/brandon-fryslie/vibedungeon-voice/claude-md"><img src="https://agentmods.dev/badge/instructions/brandon-fryslie/vibedungeon-voice/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/brandon-fryslie/vibedungeon-voice/claude-md"><img src="https://agentmods.dev/badge/instructions/brandon-fryslie/vibedungeon-voice/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,294 This file is loaded in full into every session.

When invoked 1,294 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01294	$0.01294
Opus 5	$0.00647	$0.00647
Sonnet 5	$0.00259	$0.00259
Haiku 4.5	$0.00129	$0.00129

Measured 11d ago against content hash 51a686366abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vibedungeon-voice 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 11d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 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.

Repository context

This is a personal fork of the official ElevenLabs MCP server, intended to be heavily modified to support vibedungeon, a TTRPG + LLM game. The vibedungeon codebase lives at ~/code/vibedungeon — consult it when designing tools, voice/agent flows, or audio pipelines that must integrate with the game.

Because this is a fork, do not assume upstream conventions are sacred. Prefer changes that serve vibedungeon's needs over preserving the upstream public surface. When upstream and vibedungeon needs conflict, vibedungeon wins; note removed/renamed tools in the commit message.

Commands

Setup, dev, test, and build are wrapped in scripts/:

./scripts/setup.sh — create .venv, uv pip install -e ".[dev]", install pre-commit hooks.
./scripts/dev.sh — run the server in MCP Inspector dev mode via uv run fastmcp dev elevenlabs_mcp/server.py. Use this for live tool iteration.
./scripts/test.sh [--no-coverage] [--verbose|-v] [--fail-fast|-f] — pytest with coverage by default. Run a single test with uv run pytest tests/test_utils.py::test_name -v.
./scripts/build.sh — clean dist//build/ and uv build a wheel/sdist.
Lint: uv run ruff check . and uv run ruff format . (also enforced by pre-commit).
Entry point: elevenlabs-mcp console script → elevenlabs_mcp.server:main. Module form: python -m elevenlabs_mcp generates an MCP client config (used to register the server with Claude Desktop, etc.).

Python ≥ 3.11. The project uses uv for dependency management — prefer uv run … over manually activating .venv.

Required environment

ELEVENLABS_API_KEY is required at server import time — server.py raises on import if it's unset, so even tests that import the server module need it. Use .env (loaded via python-dotenv).

Other env vars that change behavior:

ELEVENLABS_MCP_BASE_PATH — base for relative output paths (default ~/Desktop).
ELEVENLABS_MCP_OUTPUT_MODE — one of files | resources | both. Validated at import.
ELEVENLABS_API_RESIDENCY — region tag (us, eu, in, etc.); resolved by parse_location in utils.py into a base URL on the ElevenLabs client.
ELEVENLABS_DEFAULT_VOICE_ID — fallback voice for TTS tools.

Read the full file on GitHub · 57 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.

11d ago First seen · 57 lines · 1,294 tokens per session scan A 51a686366abd

Subscribe to this mod's changes

vibedungeon-voice CLAUDE.md is an instructions file published in the GitHub repository brandon-fryslie/vibedungeon-voice (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,294 tokens to every session, about $0.0065 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.

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

vibedungeon-voice: Instructions file for Claude Code