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/guycochran/x32-mcp/claude-mdgit clone --depth 1 https://github.com/guycochran/X32-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/instructions/guycochran/x32-mcp/claude-md)<a href="https://agentmods.dev/instructions/guycochran/x32-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/guycochran/x32-mcp/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 5.1 | $0.01996 | $0.01996 |
| Opus 5 | $0.00998 | $0.00998 |
| Sonnet 5 | $0.00399 | $0.00399 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
X32-MCP 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 5d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP TypeScript SDK Guide
Build & Test Commands
npm run build # Build ESM and CJS versions
npm run lint # Run ESLint
npm test # Run all tests
npx jest path/to/file.test.ts # Run specific test file
npx jest -t "test name" # Run tests matching pattern
Code Style Guidelines
- TypeScript: Strict type checking, ES modules, explicit return types
- Naming: PascalCase for classes/types, camelCase for functions/variables
- Files: Lowercase with hyphens, test files with
.test.tssuffix - Imports: ES module style, include
.jsextension, group imports logically - Error Handling: Use TypeScript's strict mode, explicit error checking in tests
- Formatting: 2-space indentation, semicolons required, single quotes preferred
- Testing: Co-locate tests with source files, use descriptive test names
- Comments: JSDoc for public APIs, inline comments for complex logic
Project description
OSC UDP Transport (raw)
↓
Address Pattern DSL (/ch/01/mix/fader)
↓
MCP Tool Layer (task-based)
MCP Tool Design Principles
Core Philosophy
Tools represent semantic user intentions, not API endpoints.
MCP tools must be designed as task-based abstractions that reflect meaningful user actions, not thin wrappers around OSC address patterns. Each tool should represent a complete, semantically meaningful operation that an LLM agent would naturally choose.
Tool Naming Convention
Pattern: <domain>_<action>
- Domain: The logical grouping (e.g.,
channel,bus,fx,main,connection) - Action: The semantic task being performed (e.g.,
set_volume,mute,get_state) - Separator: Use underscore (
_) between domain and action - Case: Use lowercase with underscores (snake_case)
Examples:
✅ GOOD - Task-based, semantic actions:
channel_set_volume # Set channel fader level
channel_set_gain # Set channel preamp gain
channel_mute # Mute/unmute a channel
channel_solo # Solo a channel
channel_get_state # Get complete channel state
channel_set_eq_band # Set specific EQ band parameters
bus_set_volume # Set bus fader level
fx_set_parameter # Set effects parameter
main_set_volume # Set main stereo fader
connection_connect # Connect to X32/M32
connection_get_info # Get mixer information
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.
- 5d ago First seen · 233 lines · 1,996 tokens per session scan A b121a672075e
X32-MCP CLAUDE.md is an instructions file published in the GitHub repository guycochran/X32-MCP (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,996 tokens to every session, about $0.0100 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 2026-08-31.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.