setup

A guided setup command for connecting Claude Code to Audacity, a desktop audio editor. It checks the required Python environment, enables Audacity’s script-pipe connection, verifies that Audacity is running, and can optionally install transcription support.

In plain words
What is it for?
Use it on first setup, when the connection is missing, or when adding optional local transcription or measurement support.
Why use it?
It walks through the separate setup conditions that can prevent the connection from working. This removes guesswork when the plugin is installed but cannot yet control Audacity.

Command

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 commands/robworks-code/audacity-mcp-max/setup
Clone the repo
git clone --depth 1 https://github.com/robworks-code/audacity-mcp-max
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.01423
Opus 5 $0.00015 $0.00711
Sonnet 5 $0.00006 $0.00285
Haiku 4.5 $0.00003 $0.00142

Measured yesterday against content hash 83903cbf42a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

commands/setup.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audacity:setup

Take the user from "plugin installed" to "Claude is editing audio" in one pass.

Three things have to be true, and each fails differently:

  1. uv is installed - the MCP server will not start without it.
  2. mod-script-pipe is enabled in Audacity - it is off by default, and Audacity only creates the script pipes at launch.
  3. Audacity is running - the pipes exist only while it is open.

If the user invoked this as /audacity:setup --transcription or /audacity:setup --measurement, do Step 4 only and stop. Those are the exact commands the tools name when an extra is missing, so someone arriving here has a working setup already and wants the one thing they are missing, not another pass over all of it. Check /audacity:doctor first for what is already installed, and name that in the sync command too - Step 4 explains why leaving it out uninstalls it.

Step 1: check uv

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/plugin_doctor.py"

If the shell reports python3: command not found, or opens a Command Line Tools install prompt instead of running anything, this machine has no python3 at all. That is a supported state - uv is what provides Python for this plugin - so do not send the user to install Python: tell them to install uv from https://docs.astral.sh/uv/, then re-run this command.

If it reports uv: not found, stop and tell the user to install it from https://docs.astral.sh/uv/ (or set UV_BIN), then restart their MCP client. Nothing else in this command matters until that is fixed.

Step 2: read the current state

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/audacity_setup.py"

This writes nothing. Read the output and decide what is needed:

  • audacity.cfg: not found - Audacity has never been run on this machine. Ask the user to open it once and close it, then run this command again.
  • mod-script-pipe: enabled - nothing to do here, go to step 4.
  • mod-script-pipe: ask - Audacity prompts on every launch and creates no pipes until someone clicks through. Treat it the same as disabled.
  • mod-script-pipe: disabled or absent - go to step 3.

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 31 tokens per session scan A 83903cbf42a5

Subscribe to this mod's changes

setup is a command published in the GitHub repository robworks-code/audacity-mcp-max (0 stars, last pushed 17d ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,423 once invoked, about $0.0002 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.