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 instructions/taylorbrook/max-msp_cc_framework/claude-mdgit clone --depth 1 https://github.com/taylorbrook/MAX-MSP_CC_FrameworkWrote 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.
[](https://agentmods.dev/instructions/taylorbrook/max-msp_cc_framework/claude-md)<a href="https://agentmods.dev/instructions/taylorbrook/max-msp_cc_framework/claude-md"><img src="https://agentmods.dev/badge/instructions/taylorbrook/max-msp_cc_framework/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.09225 | $0.09225 |
| Opus 5 | $0.04612 | $0.04612 |
| Sonnet 5 | $0.01845 | $0.01845 |
| Haiku 4.5 | $0.00923 | $0.00923 |
Grade A, and why
MAX-MSP_CC_Framework CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MAX Development Framework
This file defines how Claude works with MAX/MSP patches and code in this project. Every rule here is mandatory. When generating patches, writing GenExpr, creating RNBO exports, or scripting with Node for Max / js objects, follow these rules exactly.
Object Database
The object knowledge base lives at .claude/max-objects/ with one subdirectory per domain:
.claude/max-objects/
max/objects.json # Control flow, data, UI (470 objects)
msp/objects.json # Audio/signal processing (248 objects)
jitter/objects.json # Video, matrix, OpenGL (210 objects)
mc/objects.json # Multichannel wrappers (215 objects)
gen/objects.json # Gen~ DSP and Jitter operators (189 objects)
m4l/objects.json # Max for Live objects (33 objects)
rnbo/objects.json # RNBO export-compatible objects (560 objects)
packages/objects.json # Package objects (87 objects)
Each domain file is a JSON object keyed by object name. Every object entry contains: name, maxclass, module, domain, inlets (array with id/type/signal/hot), outlets (array with id/type/signal), arguments, messages, min_version, verified, rnbo_compatible, variable_io.
Supplementary Files
overrides.json-- Expert corrections that take precedence over extracted data. Deep-merged onto base objects.aliases.json-- Common shortcuts mapped to canonical names (e.g.,t->trigger,b->bangbang,sel->select).relationships.json-- Common object pairings and companions (e.g.,tapin~/tapout~,notein/stripnote).pd-blocklist.json-- Pure Data objects that do NOT exist in MAX, with their MAX equivalents.extraction-log.json-- Extraction metadata and statistics.
How to Use the Database
Primary method -- ObjectDatabase: Use the ObjectDatabase class from src.maxpat.db_lookup for all object lookups. It loads all 8 domain files, resolves aliases, applies overrides, and checks the PD blocklist automatically.
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.
- 4d ago First seen · 350 lines · 9,225 tokens per session scan A 40f829369a22
MAX-MSP_CC_Framework CLAUDE.md is an instructions file published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (41 stars, last pushed 8d ago), licensed MIT. It adds 9,225 tokens to every session, about $0.0461 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 instructions, from other repositories
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
carousels GEMINI.md
Instructions for sausi-7/carousels: See AGENTS.md for the full pipeline, commands and file shapes.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
video-mcp CLAUDE.md
Claude Code instructions for Zoean-z/video-mcp, a project described as: 让agent学会理解视频，无需复杂依赖和额外花费.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.