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.
npx agentmods add commands/robworks-code/audacity-mcp-max/setupgit clone --depth 1 https://github.com/robworks-code/audacity-mcp-maxWhat 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 | $0.00031 | $0.01423 |
| Opus 5 | $0.00015 | $0.00711 |
| Sonnet 5 | $0.00006 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audacity:setup
Take the user from "plugin installed" to "Claude is editing audio" in one pass.
Three things have to be true, and each fails differently:
- uv is installed - the MCP server will not start without it.
- mod-script-pipe is enabled in Audacity - it is off by default, and Audacity only creates the script pipes at launch.
- Audacity is running - the pipes exist only while it is open.
If the user invoked this as /audacity:setup --transcription or
/audacity:setup --measurement, do Step 4 only and stop. Those are the exact
commands the tools name when an extra is missing, so someone arriving here has
a working setup already and wants the one thing they are missing, not another
pass over all of it. Check /audacity:doctor first for what is already
installed, and name that in the sync command too - Step 4 explains why leaving
it out uninstalls it.
Step 1: check uv
python3 "${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: disabledorabsent- go to step 3.
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.
- yesterday First seen · 132 lines · 31 tokens per session scan A 83903cbf42a5
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.
Other commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.