max-new

max-new is a command for Claude Code from taylorbrook/MAX-MSP_CC_Framework. It costs 14 tokens per session (693 once invoked), scanned A, original, MIT.

A command for starting a new MAX/MSP project. MAX/MSP is software for building interactive audio, music, and MIDI systems with connected visual modules.

In plain words
What is it for?
Use it to scaffold a named MAX/MSP project and begin a guided discussion about its audio, MIDI, signal-flow, and interface needs.
Why use it?
It creates the initial project files and sets the project as active, so development can begin with a ready-to-open patch file.

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-new
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-new

README.md
[![agentmods](https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-new.svg)](https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-new)
Your own site
<a href="https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-new"><img src="https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-new.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 693 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 $0.00014 $0.00693
Opus 5 $0.00007 $0.00347
Sonnet 5 $0.00003 $0.00139
Haiku 4.5 $0.00001 $0.00069

Measured 3d ago against content hash 956054e2bc6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

max-new 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 3d 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-new.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/max-new

Create a new MAX/MSP project with the given name and begin the conversational kickoff phase.

Behavior

  1. Validate the project name -- must be lowercase alphanumeric with hyphens only, matching ^[a-z0-9]+(-[a-z0-9]+)*$. Reject names with leading/trailing hyphens, spaces, or uppercase letters.

  2. Create the project using the lifecycle skill and Python project module:

    • Load src/maxpat/project.py
    • Call create_project(name, base_dir) to scaffold the full directory structure under patches/{name}/
    • Call set_active_project(name, base_dir) to make this the active project
    • create_project() also creates an empty .maxpat file at patches/{name}/generated/{name}.maxpat with canvas background color set. The user can open this in MAX immediately.
    • No intermediary Python scripts are created for new projects.
  3. Start conversational kickoff -- ask the user to describe what they want to build, then ask 3-4 clarifying questions:

    • What audio/MIDI requirements does this project have? (audio input/output, MIDI in/out, both?)
    • What is the signal flow? (describe the chain from source to output)
    • Does this need a UI/presentation mode? If so, what controls?
    • Are there any specific MAX objects or techniques you want to use?
  4. Record answers -- write the user's responses to the project's context.md file in the project directory.

  5. Update status -- set the project stage to "ideation" via update_status().

  6. Flow into discuss -- after the kickoff conversation, automatically invoke /max-discuss to dive deeper into implementation decisions. Use the kickoff answers as the starting point — ask about signal flow architecture, object selection, audio design, and UI/control mapping as relevant to the project.

  7. Flow into research -- after discussion decisions are captured, automatically invoke /max-research to investigate the best MAX objects, patterns, and techniques for the approach decided in discussion. Research findings are appended to context.md.

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 14 tokens per session scan A 956054e2bc6e

Subscribe to this mod's changes

max-new is a command published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (41 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 693 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.