overview

overview is a skill for Claude Code from 8beeeaaat/touchdesigner-mcp. It costs 81 tokens per session (1,025 once invoked), scanned A, original, MIT.

A project-structure reporting skill for TouchDesigner, a visual programming tool where connected processing nodes create real-time graphics and interactive media. It summarizes the node hierarchy, operator types, and project health.

In plain words
What is it for?
Use it to review a TouchDesigner project, list its nested components, count node families, and produce a basic health report.
Why use it?
It removes the need to inspect a large TouchDesigner network manually. It gives a clear map of what the project contains and flags when the report is too large to show in full.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the touchdesigner plugin — 7 skills, 2 hooks shipped together

Good fit Use it to review a TouchDesigner project, list its nested components, count node families, and produce a basic health report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/8beeeaaat/touchdesigner-mcp/overview
Install

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.

Any agent
npx skills add 8beeeaaat/touchdesigner-mcp --skill overview
Clone the repo
git clone --depth 1 https://github.com/8beeeaaat/touchdesigner-mcp

Made for: Claude Code.

Or install touchdesigner, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

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 overview

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/8beeeaaat/touchdesigner-mcp/overview"><img src="https://agentmods.dev/badge/skills/8beeeaaat/touchdesigner-mcp/overview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,025 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 $0.00081 $0.01025
Opus 5.5 $0.00032 $0.00410
Sonnet 5.5 $0.00016 $0.00205
Haiku 4.5 $0.00008 $0.00103

Measured 25d ago against content hash 241dc256b3bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

overview 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 25d 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.

plugin/touchdesigner/skills/overview/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TD Overview

Produce a structured report of a TouchDesigner project's component hierarchy, node composition, and health.

Workflow

  1. Resolve root to the root-path argument if given, otherwise /project1 if it exists, else / (a project launched by opening the tox as a document has no /project1).

  2. Call get_td_info once for context (TouchDesigner version, OS) to include in the report header.

  3. Fetch the tree with a single get_td_nodes call on root (includeProperties: false for speed). pattern defaults to "*", and that default makes the tool return the whole subtree recursively — not just direct children — so do not loop per COMP re-fetching paths already returned. Pass pattern: "" explicitly when only the direct children of a path are wanted. Reconstruct the hierarchy from the returned path strings. If the result is too large to report in full, say so explicitly and summarize rather than silently dropping nodes.

  4. While traversing, tally node counts per operator family by matching each opType string's suffix (TOP, CHOP, SOP, POP, DAT, MAT, COMP) — this is a naming convention, not a separate field, so classify accordingly.

  5. Identify notable chains on a best-effort basis using naming and opType, since get_td_nodes doesn't report wiring/connections directly: clusters of TOPs suggesting a render network (e.g. render, camera, light, geo family nodes co-located under one COMP), or CHOP/DAT nodes suggesting an audio chain (audiofilein, audiodevicein/out, audiomovie*). Also flag COMPs whose children are almost entirely one family (a pure-TOP compositing COMP, a pure-CHOP control-rig COMP) as likely functional units worth naming in the report even without an obvious chain label. State plainly that these groupings are inferred from names and types, not verified wiring — a caveat the report should carry, not hide.

  6. Call get_td_node_errors with nodePath set to root to collect every error in the whole scope in one call (it covers descendants automatically).

Read the full file on GitHub · 34 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. 25d ago First seen · 34 lines · 81 tokens per session scan A 241dc256b3bd

Subscribe to this mod's changes

overview is a skill published in the GitHub repository 8beeeaaat/touchdesigner-mcp (582 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 1,025 once invoked, about $0.0003 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 2026-09-21.