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 skills/starrycod/cogitum/touchdesigner-mcpnpx skills add StarryCod/cogitum --skill touchdesigner-mcpgit clone --depth 1 https://github.com/StarryCod/cogitumWrote 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/skills/starrycod/cogitum/touchdesigner-mcp)<a href="https://agentmods.dev/skills/starrycod/cogitum/touchdesigner-mcp"><img src="https://agentmods.dev/badge/skills/starrycod/cogitum/touchdesigner-mcp.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 | $0.00038 | $0.04156 |
| Opus 5 | $0.00019 | $0.02078 |
| Sonnet 5 | $0.00008 | $0.00831 |
| Haiku 4.5 | $0.00004 | $0.00416 |
Grade A, and why
touchdesigner-mcp 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.
This is a copy
92% identical to touchdesigner-mcp — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TouchDesigner Integration (twozero MCP)
CRITICAL RULES
- NEVER guess parameter names. Call
td_get_par_infofor the op type FIRST. Your training data is wrong for TD 2025.32. - If
tdAttributeErrorfires, STOP. Calltd_get_operator_infoon the failing node before continuing. - NEVER hardcode absolute paths in script callbacks. Use
me.parent()/scriptOp.parent(). - Prefer native MCP tools over td_execute_python. Use
td_create_operator,td_set_operator_pars,td_get_errorsetc. Only fall back totd_execute_pythonfor complex multi-step logic. - Call
td_get_hintsbefore building. It returns patterns specific to the op type you're working with.
Architecture
Cogitum -> MCP (Streamable HTTP) -> twozero.tox (port 40404) -> TD Python
36 native tools. Free plugin (no payment/license — confirmed April 2026).
Context-aware (knows selected OP, current network).
Hub health check: GET http://localhost:40404/mcp returns JSON with instance PID, project name, TD version.
Setup (Automated)
Run the setup script to handle everything:
bash "${HERMES_HOME:-$HOME/.cogitum}/skills/creative/touchdesigner-mcp/scripts/setup.sh"
The script will:
- Check if TD is running
- Download twozero.tox if not already cached
- Add
twozero_tdMCP server to Cogitum config (if missing) - Test the MCP connection on port 40404
- Report what manual steps remain (drag .tox into TD, enable MCP toggle)
Manual steps (one-time, cannot be automated)
- Drag
~/Downloads/twozero.toxinto the TD network editor → click Install - Enable MCP: click twozero icon → Settings → mcp → "auto start MCP" → Yes
- Restart Cogitum session to pick up the new MCP server
After setup, verify:
nc -z 127.0.0.1 40404 && echo "twozero MCP: READY"
Environment Notes
- Non-Commercial TD caps resolution at 1280×1280. Use
outputresolution = 'custom'and set width/height explicitly. - Codecs:
prores(preferred on macOS) ormjpaas fallback. H.264/H.265/AV1 require a Commercial license. - Always call
td_get_par_infobefore setting params — names vary by TD version (see CRITICAL RULES #1).
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/3d-scene.md 10 KB
- references/animation.md 7.1 KB
- references/audio-reactive.md 5.0 KB
- references/dat-scripting.md 11 KB
- references/external-data.md 9.0 KB
- references/geometry-comp.md 3.5 KB
- references/glsl.md 3.5 KB
- references/layout-compositor.md 3.5 KB
- references/mcp-tools.md 30 KB
- references/midi-osc.md 7.2 KB
- references/network-patterns.md 33 KB
- references/operator-tips.md 3.5 KB
- references/operators.md 14 KB
- references/panel-ui.md 9.9 KB
- references/particles.md 8.6 KB
- references/pitfalls.md 31 KB
- references/postfx.md 4.5 KB
- references/projection-mapping.md 7.9 KB
- references/python-api.md 12 KB
- references/replicator.md 8.0 KB
- references/troubleshooting.md 7.3 KB
- scripts/setup.sh 4.4 KB runs code
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 · 357 lines · 38 tokens per session scan A 0205a3c92931
touchdesigner-mcp is a skill published in the GitHub repository StarryCod/cogitum (11 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 4,156 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to touchdesigner-mcp, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
image-resize
Use this skill when the task involves resizing, scaling, or compressing image files. Suitable for tasks like "resize these photos to 800px wide", "compress images to reduce file size", or "batch scale all JPEGs in a folder". Only relevant for image processing tasks — do NOT use for data files, text, or non-image tasks.
p5.js
Production pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, generative art, data visualizations, interactive experiences, 3D scenes, audio-reactive visuals, and motion graphics — exported as HTML, PNG, GIF, MP4, or SVG. Covers: 2D/3D rendering, noise and particle systems…
ASCII Video
Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics…
AudioCraft
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
Manim Video
Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations…
Stable Diffusion
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.