max-onboard

max-onboard is a command for Claude Code from taylorbrook/MAX-MSP_CC_Framework. It costs 16 tokens per session (523 once invoked), scanned A, original, MIT.

A command that reads a Max patch file, a project format for interactive music, sound, and multimedia, and summarizes its structure.

In plain words
What is it for?
Use it to inspect any valid .maxpat file, including object inventories, signal and control flows, nested patchers, parameters, and complexity measures.
Why use it?
It gives you an overview of a complex patch without requiring you to inspect every object and connection by hand.

Command for Claude Code

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/taylorbrook/max-msp_cc_framework/max-onboard
Clone the repo
git clone --depth 1 https://github.com/taylorbrook/MAX-MSP_CC_Framework

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 max-onboard

README.md
[![agentmods](https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-onboard.svg)](https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-onboard)
Your own site
<a href="https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-onboard"><img src="https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-onboard.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 523 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 $0.00016 $0.00523
Opus 5 $0.00008 $0.00262
Sonnet 5 $0.00003 $0.00105
Haiku 4.5 $0.00002 $0.00052

Measured 4d ago against content hash e32c18b9f662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

max-onboard 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 4d 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/commands/max-onboard.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/max-onboard

Analyze an existing .maxpat file from any source and produce a structured summary of its contents. This works on any valid .maxpat file -- project patches, downloaded patches, factory examples, or third-party patches.

Behavior

  1. Accept path -- the user provides a path to a .maxpat file. This can be any file on disk, not limited to project patches.

  2. Load patch -- read the patch file using read_patch:

    patcher, _ = read_patch(path)
    
  3. Analyze -- run the full structural analysis:

    analysis = patcher.analyze()
    
  4. Display analysis -- present the structured Markdown analysis to the user, including:

    • Complexity metrics -- object count, connection count, nesting depth
    • Object inventory -- objects grouped by domain (MSP, Max, Jitter, MC, Gen, etc.)
    • Functional sections -- named groups of related objects (e.g., "Oscillator Section", "Filter Chain")
    • Signal chain trees -- audio signal flow from sources to outputs
    • Control flow -- notable control origins (loadbang, metro, MIDI inputs) and their targets
    • Subpatcher hierarchy -- nested patchers, bpatchers, and poly~ instances
    • Parameters -- live.dial, live.slider, param, and other user-controllable parameters
  5. Offer next steps -- after displaying the analysis, offer options:

    • Create a project from this patch (sets up project directory, copies patch to generated/)
    • Start iterating on this patch with /max-iterate
    • Just review (no further action)

Python Modules

from src.maxpat import read_patch

Arguments

Argument Required Description
path-to-maxpat Yes Path to any .maxpat file (e.g., ~/Downloads/cool-synth.maxpat)

Examples

/max-onboard ~/Downloads/cool-synth.maxpat
/max-onboard patches/kicksynth/generated/kicksynth.maxpat
/max-onboard "/Applications/Max 9/examples/synths/subtractive.maxpat"

Read the full file on GitHub · 58 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. 4d ago First seen · 58 lines · 16 tokens per session scan A e32c18b9f662

Subscribe to this mod's changes

max-onboard is a command published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (41 stars, last pushed 8d ago), licensed MIT. It adds 16 tokens to every session and 523 once invoked, about $0.0001 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 2026-08-30.