agentmods.dev

MAX-MSP_CC_Framework: Command for Claude Code

.claude/commands/max-verify.md

max-verify is a command for Claude Code from taylorbrook/MAX-MSP_CC_Framework. It costs 12 tokens per session (1,665 once invoked), scanned A, original, MIT.

A command that validates generated Max/MSP files, including visual patches, JavaScript, and Gen code. Max/MSP is software for building music and multimedia systems.

In plain words
What is it for?
Checking files in the active project, grouping issues as blockers, warnings, or notes, and recording the verification result.
Why use it?
It brings structural checks and critic findings into one review, so invalid files and likely problems are easier to find before use.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is taylorbrook/MAX-MSP_CC_Framework's own configuration. It tells Claude Code how to work on MAX-MSP_CC_Framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MAX-MSP_CC_Framework configures →

not rated 46repo changed 6d ago A scan 12 tokens original MIT
View source ↗ taylorbrook/MAX-MSP_CC_Framework
Reuse

Borrowing it

Nothing to install: this file belongs to taylorbrook/MAX-MSP_CC_Framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/taylorbrook/MAX-MSP_CC_Framework/main/.claude/commands/max-verify.md
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-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-verify/github.svg)](https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-verify)
Your own site
<a href="https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-verify"><img src="https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for max-verify

Your own site · 80×15
<a href="https://agentmods.dev/commands/taylorbrook/max-msp_cc_framework/max-verify"><img src="https://agentmods.dev/badge/commands/taylorbrook/max-msp_cc_framework/max-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.01665
Opus 5.5 $0.00005 $0.00666
Sonnet 5.5 $0.00002 $0.00333
Haiku 4.5 $0.00001 $0.00167

Measured 6d ago against content hash 6d7cbd032aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

max-verify 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 6d 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-verify.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/max-verify

Run the full validation pipeline and critic review on all generated files in the active project.

Behavior

  1. Load active project -- read patches/.active-project.json for the current project. If no active project, prompt the user.

  2. Find generated files -- scan the project's generated/ directory for all .maxpat, .gendsp, and .js files.

  3. Run mechanical validation -- for each file:

    • .maxpat files: call validate_file() from src.maxpat to check JSON structure, object validity, connection bounds. It passes the file's path, so an unknown object that no abstraction beside the patch (or in its project) resolves is an error, and treats codeboxes as loaded (tab lines warn)
    • .js / .gendsp files: call validate_code_file() from src.maxpat for code-level validation (a .gendsp on disk is loaded code: tab lines warn)

  4. Run critic review -- invoke the max-critic skill:

    • Call review_patch(patch_dict, code_context) from src.maxpat.critics (default is_new=False for committed files; pass is_new=True for a patch that has never been saved, so an uninitialized control is reported as the blocker the save gate will raise)
    • Collect all CriticResult findings across files

  5. Display results grouped by severity:

    • Blockers -- must be fixed before the patch will work correctly. Suggest specific fixes.
    • Warnings -- potential issues that may cause unexpected behavior. Annotate with explanation.
    • Notes -- informational observations about style or best practices.

  6. Update status -- record verification results in project status.

  7. Live check (opt-in, --live) -- only with --live, and only after steps 3-5 have printed the static report:

    • Run python3 tools/max_verify_live.py --json plus the pass-through flags (--record S, --note P V, --no-shot, --live-inputs). Give no PATH: the tool reads the same active-project pointer and drops the abstractions and bpatcher children that a sibling references, so only top-level patches are loaded.
    • Exit 0 or 1 -- append a "Live check (MAX 9.2):" section built from the JSON: per patch, the LIVE BLOCKER / LIVE WARNING / LIVE NOTE lines with their suggestions, the shot path and the run dir. Optionally Read each shot PNG to eyeball the layout, and flag visual issues.
    • Exit 2 -- one line: live check skipped: <hint> (no bridge, MAX not running, toggle OFF), or live check aborted: <hint> plus the not-checked patches. The static report and its counts stay exactly as they were.
    • A file that is not a readable patch (truncated JSON, undecodable bytes, non-patch JSON) is listed as refused with one cannot read <path>: ... note, and the batch goes on.
    • Live findings are report-only (.claude/skills/references/severity-contract.md section 7): never feed them into the critic revision loop, never change step 6's status record from them, and never auto-fix. Offer /max-iterate for the fixes.

Read the full file on GitHub · 119 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. 6d ago Changed · +1 lines 6d7cbd032aa0
  2. 8d ago Changed · +51 lines 23130a96bbbd
  3. 2mo ago First seen · 67 lines · 12 tokens per session scan A 4b5ff2918150

Subscribe to this mod's changes

max-verify is a command published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (46 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 1,665 once invoked, about $0.0000 per session on Opus 5.5. 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.

Testing
Related

Other commands, from other repositories

prototype

You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

grainulation/grainulator · 0 tokens

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

verify

Run repository verification using the verification-loop skill.

cloudnative-co/claude-code-starter-kit · 9 tokens

modernize-transform

Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.

fuxicodex/Fuxi · 17 tokens

constraints

A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.

vinvcn/addyosmani-agent-skills-zh · 20 tokens

check-dev

Type-check a Z specification with fuzz.

punt-labs/z-spec · 7 tokens