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.
curl -O https://raw.githubusercontent.com/taylorbrook/MAX-MSP_CC_Framework/main/.claude/skills/max-critic/SKILL.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/skills/taylorbrook/max-msp_cc_framework/max-critic)<a href="https://agentmods.dev/skills/taylorbrook/max-msp_cc_framework/max-critic"><img src="https://agentmods.dev/badge/skills/taylorbrook/max-msp_cc_framework/max-critic/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.
<a href="https://agentmods.dev/skills/taylorbrook/max-msp_cc_framework/max-critic"><img src="https://agentmods.dev/badge/skills/taylorbrook/max-msp_cc_framework/max-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00020 | $0.01757 |
| Opus 5.5 | $0.00008 | $0.00703 |
| Sonnet 5.5 | $0.00004 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00176 |
Grade A, and why
max-critic 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic Orchestrator Agent
The critic agent runs the generate-review-revise loop on generated output before the user sees it. It invokes deterministic Python critic modules (not LLM judgment) for signal flow and structure analysis, then requests revisions from the generator for any blocker-level findings.
Context Loading
Before running the critic loop:
- Read
src/maxpat/critics/__init__.pyforreview_patch()andCriticResult - Read the generated patch dict or code output from the generator
- No object database loading needed -- critics use the DB internally
Capabilities
- Invoke
review_patch(patch_dict, code_context=None, ext_code=None, ext_archetype="message", is_new=...)fromsrc.maxpat.critics:is_new=Truewhen the output will be saved as a new file (/max-build, or an iterate step that creates a file),is_new=False(the default) for an edit of an existing file. It must match what the save gate will use (True for a file with no baseline), or a Q24 uninitialized-state warning in the loop becomes a refused save - Parse the returned
list[CriticResult]for severity levels: blocker, warning, note - Format blocker findings into actionable revision requests for the generator
- Track revision history to detect repeated identical findings
- Report warnings and notes in the review summary (finding plus suggestion); never write them into the patch or code
- The DSP, structure and layout critics always run, on every non-gen scope (findings carry
path) - The RNBO critic (
review_rnbo) auto-invokes when rnbo~ boxes are detected in the patch - The M4L critic (
review_m4l) auto-invokes whenplugin~,plugout~orlive.thisdeviceis found in any scope; alive.thisdevice-only patch is a helper abstraction and gets only the per-scope checks and parameter-name uniqueness - The package critic (
review_packages) auto-invokes when package objects (BEAP, Bach, community) are detected in the patch - The external critic (
review_external) invokes whenext_codeis provided
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.
- 6d ago Changed · +22 lines 59e29d928765
- 14d ago Changed · +3 lines 452f1ee03596
- 16d ago Changed 719552316804
- 2mo ago First seen · 85 lines · 20 tokens per session scan A 6c019a7d7e37
max-critic is a skill published in the GitHub repository taylorbrook/MAX-MSP_CC_Framework (46 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 1,757 once invoked, about $0.0001 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.