Borrowing it
Nothing to install: this file belongs to ersatzben/maxmsp-mcp. 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/ersatzben/maxmsp-mcp/main/.claude/skills/maxmsp/SKILL.mdgit clone --depth 1 https://github.com/ersatzben/maxmsp-mcpWrote 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/ersatzben/maxmsp-mcp/maxmsp)<a href="https://agentmods.dev/skills/ersatzben/maxmsp-mcp/maxmsp"><img src="https://agentmods.dev/badge/skills/ersatzben/maxmsp-mcp/maxmsp/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/ersatzben/maxmsp-mcp/maxmsp"><img src="https://agentmods.dev/badge/skills/ersatzben/maxmsp-mcp/maxmsp.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 | $0.00029 | $0.00989 |
| Opus 5.5 | $0.00012 | $0.00396 |
| Sonnet 5.5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
maxmsp 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 2mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY CHECKLIST - Follow Before EVERY Action
BEFORE placing ANY object:
0. Consider whether the task at hand is best served by using a subpatcher.
1. Call get_avoid_rect_position() FIRST
2. Use returned [left, top, right, bottom] to calculate position
3. Place at y = bottom + 50 (minimum)
NEVER skip this step. NEVER guess positions.
Required acknowledgment flags:
Math objects (+, -, *, /, %, pow, scale) and pack/pak/unpack:
- JSON strips
.0from numbers! Use STRING args:["0", "127", "0", "25."] - Strings with
.are converted to floats, without.to ints - For unpack, use
["f", "f", "f"](type specifier) - Set
int_mode=Trueif integer truncation is intentional - Exception:
scalewith output range ≤ 2 auto-detects float intent
dial - use instead of live.dial, requires @size:
- Float 0-1:
['@size', 1, '@floatoutput', 1] - Bipolar -1 to 1:
['@min', -1, '@size', 2, '@floatoutput', 1, '@mode', 6] - Int 0-127:
['@size', 127] - Max @size 255 - larger creates unusable UI; use
flonum/numberinstead (bypass withextend=True) live.dialrejected (bypass withuse_live_dial=True)
trigger/t - fires RIGHT-TO-LEFT:
- Set
trigger_rtl=Trueto acknowledge [t b f]sendsfFIRST, thenb
random - needs BANG to trigger (numbers only set range):
- Set
random_bang=Trueto acknowledge - Use
[t b]to convert numbers to bangs beforerandom
coll - data doesn't persist unless embedded:
- Always include
@embed 1in args:['mycoll', '@embed', 1]
Signal Flow Rules
Auto-summing: MSP inlets automatically sum all incoming signals. Never use +~ just to combine signals - connect them both to the same inlet instead.
Delay feedback: Connect feedback directly to tapin~, never through a mixer first.
Placement Rules
After calling get_avoid_rect_position() → [left, top, right, bottom]:
- First object:
[left, bottom + 50] - Same row: x += previous_width + 25
- New row: x = left, y += 50
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.
- 2mo ago First seen · 103 lines · 29 tokens per session scan A ba783f6f593a
maxmsp is a skill published in the GitHub repository ersatzben/maxmsp-mcp (172 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 989 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.
maxmsp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maxmspersatzben/maxmsp-mcp | Skill | 172 | 4mo ago | MIT | A | 29 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |