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/8beeeaaat/touchdesigner-mcp/claude-mdgit clone --depth 1 https://github.com/8beeeaaat/touchdesigner-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/8beeeaaat/touchdesigner-mcp/claude-md)<a href="https://agentmods.dev/instructions/8beeeaaat/touchdesigner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/8beeeaaat/touchdesigner-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 | $0.02156 | $0.02156 |
| Opus 5 | $0.01078 | $0.01078 |
| Sonnet 5 | $0.00431 | $0.00431 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
touchdesigner-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 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
Building and Development
npm run build- Full build process including code generation and TypeScript compilation (recommended for development)npm run dev- Start MCP inspector for debugging (@modelcontextprotocol/inspector)make build- Docker-based build that copies bothdist/andtd/modules/from container (for CI/CD)npm run build:mcpb- Build MCP Bundle package for distributionmake clean- Remove all generated files (dist,td/modules,node_modules)
Code Generation Workflow
The project uses OpenAPI 3.0.0 schema-based code generation with a three-step process:
npm run gen:openapi- Bundle OpenAPI schema files into single YAML using@redocly/clinpm run gen:handlers- Generate Python handlers using custom Node.js script with Mustache templatesnpm run gen:mcp- Generate TypeScript client code and Zod schemas using Orval v8npm run gen- Run all generation steps in sequence
Testing and Quality
npm test- Run all tests (e2e, integration and unit)npm run test:e2e- E2E tests: buildsdist/and drives the builtdist/cli.jswith the real MCP SDK v2 client over stdio and Streamable HTTP (both protocol eras; no TouchDesigner required)npm run test:integration- Integration tests with TouchDesigner WebServernpm run test:unit- Unit tests for MCP server componentsnpm run coverage- Generate test coverage report
HTTP Transport Mode
npm run http- Build and start the MCP server in HTTP mode (port 6280, TD on 9981)npm run test:integration- Includes the HTTP transport suite (tests/integration/httpTransport.test.ts)
HTTP Mode Configuration:
- Default port:
3000 - Default host:
127.0.0.1 - Endpoint:
/mcp - Health check:
GET /health
Linting and Formatting
The project uses multiple formatters and linters for different languages:
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 First seen · 163 lines · 2,156 tokens per session scan A 0b011378f352
touchdesigner-mcp CLAUDE.md is an instructions file published in the GitHub repository 8beeeaaat/touchdesigner-mcp (517 stars, last pushed 29d ago), licensed MIT. It adds 2,156 tokens to every session, about $0.0108 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 instructions, from other repositories
Embody CLAUDE.md
Claude Code instructions for dylanroscover/Embody, covering embody + envoy, project overview, critical rules, approach guidelines and project structure.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Claude Code instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).