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/taylorbrook/max-msp_cc_framework/max-researchgit clone --depth 1 https://github.com/taylorbrook/MAX-MSP_CC_FrameworkWhat 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 | $0.00014 | $0.00512 |
| Opus 5 | $0.00007 | $0.00256 |
| Sonnet 5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
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.
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
-
Load active project -- read
patches/.active-project.jsonto identify the current project. If no active project, prompt the user to create one with/max-new. -
Load project context -- read the project's
context.mdfor existing context and decisions. -
Research MAX approaches -- investigate the topic using the object database:
- Read relevant domain files from
.claude/max-objects/(msp, gen, max, etc.) - Check
relationships.jsonfor common object pairings - Check
aliases.jsonfor shorthand references - Look up specific objects for inlet/outlet counts, arguments, messages
- Consult the PD blocklist to avoid Pure Data object confusion
- Read relevant domain files from
-
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
-
Write findings to context -- append research results to the project's
context.mdunder a "Research" section. -
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, UImsp/objects.json-- audio/signal processinggen/objects.json-- Gen~ DSP operatorsjitter/objects.json-- video, matrix, OpenGLmc/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
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.
- 3d ago First seen · 67 lines · 14 tokens per session scan A a2ff1fc3140a
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.