max-research

max-research is a command for Claude Code from taylorbrook/MAX-MSP_CC_Framework. It costs 14 tokens per session (512 once invoked), scanned A, original, MIT.

A command that researches MAX/MSP techniques and relevant objects for the active project. MAX/MSP is software for building audio, music, and multimedia systems by connecting visual programming objects.

In plain words
What is it for?
Use it to investigate approaches, compare techniques, check object details, and save the findings in the project context.
Why use it?
It helps identify suitable objects, signal-flow patterns, alternatives, and MAX 9 compatibility details before building.

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

Made for: Claude Code.

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 512 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 $0.00512
Opus 5 $0.00007 $0.00256
Sonnet 5 $0.00003 $0.00102
Haiku 4.5 $0.00001 $0.00051

Measured 3d ago against content hash a2ff1fc3140a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

max-research 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-research.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-research

Research MAX-specific approaches, object choices, signal flow patterns, and techniques relevant to the active project.

Behavior

  1. Load active project -- read patches/.active-project.json to identify the current project. If no active project, prompt the user to create one with /max-new.

  2. Load project context -- read the project's context.md for existing context and decisions.

  3. Research MAX approaches -- investigate the topic using the object database:

    • Read relevant domain files from .claude/max-objects/ (msp, gen, max, etc.)
    • Check relationships.json for common object pairings
    • Check aliases.json for shorthand references
    • Look up specific objects for inlet/outlet counts, arguments, messages
    • Consult the PD blocklist to avoid Pure Data object confusion
  4. Present findings -- summarize research results including:

    • Recommended objects and why
    • Signal flow patterns for the approach
    • Alternative techniques with tradeoffs
    • Any version compatibility notes for MAX 9 objects used
  5. Write findings to context -- append research results to the project's context.md under a "Research" section.

  6. Update status -- set the project stage to "research" via update_status().

Skills Referenced

  • max-lifecycle -- project context loading, status tracking

Object Database

Read from .claude/max-objects/ domains as needed:

  • max/objects.json -- control flow, data, UI
  • msp/objects.json -- audio/signal processing
  • gen/objects.json -- Gen~ DSP operators
  • jitter/objects.json -- video, matrix, OpenGL
  • mc/objects.json -- multichannel wrappers

Python Modules

from src.maxpat.project import get_active_project, read_status, update_status

Arguments

Argument Required Description
topic No Research focus (e.g., "granular synthesis approaches")

Examples

/max-research granular synthesis approaches
/max-research MIDI mapping patterns
/max-research gen~ waveshaping techniques
/max-research

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 a2ff1fc3140a

Subscribe to this mod's changes

max-research 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 512 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.