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 skills/taylorbrook/max-msp_cc_framework/max-ext-agentnpx skills add taylorbrook/MAX-MSP_CC_Framework --skill max-ext-agentgit 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/skills/taylorbrook/max-msp_cc_framework/max-ext-agent)<a href="https://agentmods.dev/skills/taylorbrook/max-msp_cc_framework/max-ext-agent"><img src="https://agentmods.dev/badge/skills/taylorbrook/max-msp_cc_framework/max-ext-agent.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 | $0.00020 | $0.01129 |
| Opus 5 | $0.00010 | $0.00564 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
max-ext-agent 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Externals Specialist Agent
Scaffold, generate, build, and validate C++ externals using the Min-DevKit. Supports three archetypes (message, dsp, scheduler) with automated build loops, .mxo validation, and help patch generation.
Capabilities
- Min-DevKit scaffolding: Create complete project directories with source, CMake, and help files via
scaffold_external - Three archetypes: message (control objects), dsp (signal processing), scheduler (timed events)
- Code generation: Generate archetype-specific C++ source via
generate_external_code - Build and compile: Automated cmake/make build loop with error parsing and auto-fix via
build_external - Min-DevKit setup: Initialize git submodule for Min-DevKit via
setup_min_devkit - .mxo validation: Post-compile binary validation (Mach-O type, arm64 architecture) via
validate_mxo - Help patch generation: Create .maxhelp demonstration patches via
generate_help_patch - Code review: Run external critic for structural code issues
Shared Capabilities: See
.claude/skills/references/shared-capabilities.mdfor Z-Order Manipulation, Aesthetic Capabilities, Layout Options, Editing Functions, and Edit Workflow reference.
Domain Context Loading
When invoked:
- Read
CLAUDE.mdexternals section for conventions and patterns - No object database needed -- externals are custom objects not in the DB
Python API References
from src.maxpat.externals import (
scaffold_external,
generate_external_code,
build_external,
setup_min_devkit,
generate_help_patch,
)
from src.maxpat.ext_validation import (
validate_mxo,
BuildResult,
)
from src.maxpat.critics import review_patch
from src.maxpat.critics.ext_critic import review_external
Key Functions
scaffold_external(project_dir, name, archetype, description): Creates complete project directory structuregenerate_external_code(name, archetype, description, **kwargs): Returns C++ code stringsetup_min_devkit(ext_dir): Initializes Min-DevKit as a git submodulebuild_external(ext_dir, max_attempts=5): cmake/make build loop with auto-fix and loop detectionvalidate_mxo(mxo_path): Post-compile .mxo bundle validationgenerate_help_patch(name, archetype): Builds a demonstration .maxhelp Patcherreview_external(code_str, archetype): Semantic code review for structural issuesBuildResult: Dataclass with success, mxo_path, errors, attempts, message
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 109 lines · 20 tokens per session scan A c53454343f10
max-ext-agent is a skill published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (41 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 1,129 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 skills, from other repositories
cpp-pro
Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance…
add-uint-support
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
at-dispatch-v2
Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code. Use when porting ATDISPATCHALLTYPESAND, ATDISPATCHFLOATINGTYPES, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
sqlitecpp-doxygen-guide
SQLiteCpp Doxygen standards and templates for public API docs and file headers.
cuda-index-width
Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64t, canUse32BitIndexMath, CUDAKERNELLOOPTYPE, or ATDISPATCHINDEXTYPES, and when considering binary-size or performance impact of index-type templating.
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…