touchdesigner-agent-mcp: Instructions file for Claude Code

CLAUDE.md

touchdesigner-agent-mcp CLAUDE.md is an instructions file for Claude Code from axysar/touchdesigner-agent-mcp. It costs 1,029 tokens per session, scanned A, original, MIT.

Project instructions for touchdesigner-agent-mcp, a Python bridge that lets coding agents drive TouchDesigner. They describe the server, its TouchDesigner-side code, the shared JSON request format, and how to modify its tools.

In plain words
What is it for?
Working on the bridge's server, client, configuration, prompts, tool modules, and TouchDesigner web-server code, including adding or changing a tool.
Why use it?
They give an agent the repository layout and operating rules needed to understand changes without guessing how the bridge is organized.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is axysar/touchdesigner-agent-mcp's own configuration. It tells Claude Code how to work on touchdesigner-agent-mcp 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 touchdesigner-agent-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to axysar/touchdesigner-agent-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.

Copy the file
curl -O https://raw.githubusercontent.com/axysar/touchdesigner-agent-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/axysar/touchdesigner-agent-mcp

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 touchdesigner-agent-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/axysar/touchdesigner-agent-mcp/claude-md.svg)](https://agentmods.dev/instructions/axysar/touchdesigner-agent-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/axysar/touchdesigner-agent-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/axysar/touchdesigner-agent-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,029 This file is loaded in full into every session.
When invoked 1,029 The same file — it is already loaded in full.
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 $0.01029 $0.01029
Opus 5 $0.00515 $0.00515
Sonnet 5 $0.00206 $0.00206
Haiku 4.5 $0.00103 $0.00103

Measured 7d ago against content hash c95155c9cbb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

touchdesigner-agent-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 7d 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.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in the touchdesigner-agent-mcp repository.

What this is

A pure-Python MCP server that drives TouchDesigner. Two halves:

  • Host (src/td_agent_mcp/) — the MCP server (FastMCP). Runs wherever the MCP client runs. Defines tools/prompts and an async HTTP client to TD.
  • TouchDesigner side (td/) — plain Python loaded by a Web Server DAT inside TouchDesigner. Executes the actual operator calls.

They speak one JSON contract: POST /mcp {op, params}{ok, data, error}. There is no codegen (no OpenAPI/orval/mustache/Docker) — that is the point.

Layout

src/td_agent_mcp/
  cli.py          entry point (--stdio default, --http)
  server.py       build_server(): FastMCP + register every tool module + prompts
  client.py       TDClient: async httpx wrapper, {ok,data,error}, TDError
  config.py       env/CLI settings (TD_HOST/TD_PORT/TD_TIMEOUT)
  formatting.py   ResponseFormat + json/markdown rendering (shared)
  prompts.py      3 MCP prompts
  tools/          one module per group; each exposes register(mcp, client)
td/
  webserver.py    Web Server DAT callbacks (onHTTPRequest/Start/Stop)
  router.py       op-name -> handler table; {ok,data,error} envelope
  ops.py          base operations (node CRUD, python exec, introspection)
  forkops.py      extended ops (pane, cook, viewport, connect, layout, glsl, scaffold)
  tdapi.py        TD helper library (docked-aware create/move, layout, cook)
  install.py      builds the Web Server DAT component inside TD

Commands

uv sync                       # deps + dev tools (uv, not pip)
uv run touchdesigner-agent-mcp --help
uv run pytest                 # registration tests (no TouchDesigner needed)
uv run ruff check . && uv run ruff format .
python -m py_compile td/*.py  # syntax-check the TD-side modules

There is no test runner that touches a live TouchDesigner — the td/ modules import TD builtins (td, op, ui, operator-type constants) that only exist inside TouchDesigner. Verify host-side logic with pytest; syntax-check td/ with py_compile; integration must be done with TouchDesigner running.

Read the full file on GitHub · 84 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. 7d ago First seen · 84 lines · 1,029 tokens per session scan A c95155c9cbb5

Subscribe to this mod's changes

touchdesigner-agent-mcp CLAUDE.md is an instructions file published in the GitHub repository axysar/touchdesigner-agent-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,029 tokens to every session, about $0.0051 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens