touchdesigner-mcp: Skill for Claude Code

.claude/skills/touchdesigner-self-debug/SKILL.md

touchdesigner-self-debug is a skill for Claude Code from 8beeeaaat/touchdesigner-mcp. It costs 134 tokens per session (2,194 once invoked), scanned A, original, MIT.

A workflow for testing Python changes inside TouchDesigner, a visual application for building interactive graphics and media. It starts or connects to TouchDesigner, runs the real code, and checks the resulting values in the application.

In plain words
What is it for?
Checking changes to TouchDesigner Python modules and confirming that nodes, outputs, or error states match the expected result.
Why use it?
It catches problems that ordinary offline tests can miss by verifying what TouchDesigner actually does at runtime.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is 8beeeaaat/touchdesigner-mcp's own configuration. It tells Claude Code how to work on touchdesigner-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-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 8beeeaaat/touchdesigner-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/8beeeaaat/touchdesigner-mcp/main/.claude/skills/touchdesigner-self-debug/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/8beeeaaat/touchdesigner-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-self-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug/github.svg)](https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug)
Your own site
<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug/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 touchdesigner-self-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/touchdesigner-self-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,194 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00134 $0.02194
Opus 5.5 $0.00054 $0.00878
Sonnet 5.5 $0.00027 $0.00439
Haiku 4.5 $0.00013 $0.00219

Measured 1mo ago against content hash 305944d0b671, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

touchdesigner-self-debug 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/touchdesigner-self-debug/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TouchDesigner Startup + Functional Self-Debugging

A general technique for verifying any TD-side Python change (e.g. anything in td/modules/**) inside real TouchDesigner. Calling functions directly from the Textport, without standing up the HTTP WebServer, is the shortest path.

This skill is feature-agnostic. The worked example in Steps 4–5 happens to verify node auto-alignment (the PR that produced this skill), but that is illustration only. The reusable shape is: create/modify via the real code path → read back the TD runtime value you actually care about → reconcile against an invariant. Swap the alignment-specific bits (grid, overlap area, node_layout.py) for whatever your change touches. Do not assume alignment, grids, or overlap have anything to do with your task.

When to Execute

  • You modified TD-side logic (e.g. td/modules/mcp/services/*.py) and want to check behavior on the real machine.
  • Unit/offline verification is insufficient and you need to reconcile against TD runtime data (any node attribute, cook result, error state, etc.).
  • You are in a fresh worktree that cannot rely on CI or the 9981-dependent integration suite.

Prerequisites and Pitfalls (read first — these are general)

  1. The .tox reads td/modules/ from disk at runtime. Re-authoring the .tox is not required for .py changes; reload modules or restart TD.
  2. loadTox() leaves externaltox empty → import_modules.setup() fails with No module named 'mcp'. Replicate setup manually (Step 3).
  3. A fresh worktree lacks generated artifacts → empty OpenAPI schema / missing node_modules breaks HTTP routing. Bypass it by calling the Textport directly (Step 4). Only run npm install && npm run gen if you specifically need the HTTP path (e.g. running the vitest integration suite).
  4. Computer-use screenshots go black when TD loses frontmost focus → recover with open_application("TouchDesigner") + switch_display.
  5. Multi-line pastes into the REPL break on line boundaries → always wrap in exec("""...""") to submit as one statement.
  6. To pick up a later .py edit in an already-running TD, drop the module from sys.modules so the next import reloads from disk (Step 3c). If the WebServer is already up you can do this via execute_python_script — no computer-use needed.

Read the full file on GitHub · 162 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. 1mo ago First seen · 162 lines · 134 tokens per session scan A 305944d0b671

Subscribe to this mod's changes

touchdesigner-self-debug is a skill published in the GitHub repository 8beeeaaat/touchdesigner-mcp (601 stars, last pushed 13d ago), licensed MIT. It adds 134 tokens to every session and 2,194 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

idapython

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…

mrexodia/ida-pro-mcp · 77 tokens

operator-gotchas

MUST READ before wiring a TOP, CHOP, MAT, DAT, light, camera or instancing chain you have not built before: the parameter names TD abbreviates, the defaults that silently do the wrong thing, and the input-order rules, per operator, verified on TD 2025.33230. Pair with describeoptype.

dylanroscover/Embody · 74 tokens

debug-operator

TRIGGER when operator errors appear or user reports broken behavior. Systematic diagnosis workflow.

dylanroscover/Embody · 21 tokens

python-explore

Use when understanding, navigating, debugging, refactoring, or extending Python code with the pyeye MCP server. Triggers on "how does X work", "what does", "why is X doing", "what calls/imports/subclasses this", "add feature", "implement", "refactor", "trace", "debug", "extend". Does NOT trigger for explicit "show…

okeefeco/pyeye-mcp · 144 tokens

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens

plugin-architecture-patterns

Design, implement, or diagnose Xberg plugin traits, typed registries, priority collisions, lifecycle, native extractors, and Alef-generated Python plugin bridges. Load for plugin-system work, not ordinary extractor parsing.

xberg-io/xberg · 43 tokens