touchdesigner-mcp-server: Command for Claude Code

.claude/commands/td-mcp-improvement.md

td-mcp-improvement is a command for Claude Code from bottobot/touchdesigner-mcp-server. It costs 5 tokens per session (2,395 once invoked), scanned A, original, MIT.

A workflow guide for improving the TouchDesigner MCP server, a tool that lets coding agents work with TouchDesigner projects. It describes the order of tasks and how different workflow steps should run.

In plain words
What is it for?
Use it to guide work on versioning, an experimental knowledge base, core tools, experimental builds, validation, and documentation for the TouchDesigner MCP server.
Why use it?
It removes guesswork from carrying out a multi-step server improvement process. Developers can see when to analyze code, implement changes, validate them, and update documentation.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool.

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/robert/Documents/TD-MCP/touchdesigner-mcp-server..

Reuse

Borrowing it

Nothing to install: this file belongs to bottobot/touchdesigner-mcp-server. 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/bottobot/touchdesigner-mcp-server/main/.claude/commands/td-mcp-improvement.md
Clone the repo
git clone --depth 1 https://github.com/bottobot/touchdesigner-mcp-server

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 td-mcp-improvement

README.md
[![agentmods](https://agentmods.dev/badge/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement/github.svg)](https://agentmods.dev/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement)
Your own site
<a href="https://agentmods.dev/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement"><img src="https://agentmods.dev/badge/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement/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.

agentmods 80×15 button for td-mcp-improvement

Your own site · 80×15
<a href="https://agentmods.dev/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement"><img src="https://agentmods.dev/badge/commands/bottobot/touchdesigner-mcp-server/td-mcp-improvement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,395 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00005 $0.02395
Opus 5 $0.00003 $0.01197
Sonnet 5 $0.00001 $0.00479
Haiku 4.5 $0.00001 $0.00239

Measured 10d ago against content hash 04db645a6ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

td-mcp-improvement 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 10d 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/commands/td-mcp-improvement.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flowchart TD
    start_node_default([Start])
    analyze_codebase[Sub-Agent: analyze-codebase]
    implement_version_system[Sub-Agent: implement-version-system]
    implement_experimental_kb[Sub-Agent: implement-experimental-kb]
    implement_core_tools[Sub-Agent: implement-core-tools]
    implement_experimental_builds[Sub-Agent: implement-experimental-builds]
    validate_changes[Sub-Agent: validate-changes]
    update_documentation[Sub-Agent: update-documentation]
    completion_prompt[TD MCP Server v2.8.0 improv...]
    end_node_default([End])

    start_node_default --> analyze_codebase
    analyze_codebase --> implement_version_system
    implement_version_system --> implement_experimental_kb
    implement_experimental_kb --> implement_core_tools
    implement_core_tools --> implement_experimental_builds
    implement_experimental_builds --> validate_changes
    validate_changes --> update_documentation
    update_documentation --> completion_prompt
    completion_prompt --> end_node_default

Workflow Execution Guide

Follow the Mermaid flowchart above to execute the workflow. Each node type has specific execution methods as described below.

Execution Methods by Node Type

  • Rectangle nodes (Sub-Agent: ...): Execute Sub-Agents
  • Diamond nodes (AskUserQuestion:...): Use the AskUserQuestion tool to prompt the user and branch based on their response
  • Diamond nodes (Branch/Switch:...): Automatically branch based on the results of previous processing (see details section)
  • Rectangle nodes (Prompt nodes): Execute the prompts described in the details section below

Sub-Agent Node Details

analyze_codebase(Sub-Agent: analyze-codebase)

Description: Analyzes current TD MCP Server state and plans improvements

Model: sonnet

Prompt:

Analyze the current state of the TouchDesigner MCP Server project at /home/robert/Documents/TD-MCP/touchdesigner-mcp-server. Read CHANGELOG.md, README.md, MCP-ARCHITECTURE.md, package.json, and scan the tools/ and wiki/data/ directories. Identify: (1) the 12 existing tools and their capabilities, (2) improvements already made in v2.7.0, (3) the five planned improvement streams: Version System, Experimental Techniques KB, Core Tool Enhancements, Experimental Build Support, and All Streams Combined. Return a concise summary of current state and confirm readiness to proceed with all improvements automatically.

Read the full file on GitHub · 145 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. 10d ago First seen · 145 lines · 5 tokens per session scan A 04db645a6ff6

Subscribe to this mod's changes

td-mcp-improvement is a command published in the GitHub repository bottobot/touchdesigner-mcp-server (77 stars, last pushed 21d ago), licensed MIT. It adds 5 tokens to every session and 2,395 once invoked, about $0.0000 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.