Borrowing it
Nothing to install: this file belongs to mrinalghosh/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.
curl -O https://raw.githubusercontent.com/mrinalghosh/touchdesigner-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/mrinalghosh/touchdesigner-mcpWrote 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/instructions/mrinalghosh/touchdesigner-mcp/claude-md)<a href="https://agentmods.dev/instructions/mrinalghosh/touchdesigner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mrinalghosh/touchdesigner-mcp/claude-md.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 5.1 | $0.00796 | $0.00796 |
| Opus 5 | $0.00398 | $0.00398 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
touchdesigner-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TouchDesigner MCP — Agent Guidance
Rules for Claude sessions working against this repo's MCP bridge. These are hard-won gotchas; ignore them and things break silently.
Parameter names are lowercase internal names
mcp__touchdesigner__set_parameter requires the lowercase internal param name as returned by list_parameters (e.g. brightness1, gamma1, translatex). Do not use the TitleCase form (Brightness1) — the tool docstring is misleading.
- The server does
getattr(op.par, param)directly and it is case-sensitive. Brightness1→tdAttributeError: 'td.ParCollection' object has no attribute 'Brightness1'.- If unsure, call
list_parametersfirst and copy thenamefield verbatim. - If the user says "set Brightness to 0.6", translate to
brightness1before calling.
GLSL TOP uniforms: use the Vectors page, not Constants
For runtime-updatable uniforms in a GLSL TOP, use the Vectors page — the Constants page is compile-time #define-style only.
- Constants page symptom:
Warning: Uniform 'X' is not assigned. Please assign it on the Colors or Vectors page.Shader compiles but the uniform is never supplied. - Correct setup: declare
uniform vec4 uName;in the shader, setvec0name='uName', read asuName.x(or.xy,.xyz,.xyzw). - Bind
vec0valuex(etc.) via expression to the CHOP channel. - Scalars aren't supported as runtime uniforms — wrap them in a vec4.
- Colors page works the same way for vec4 color values.
Insert a Null CHOP after source CHOPs
When wiring CHOP references into expressions, parameters, or other ops, place a Null CHOP between the source CHOP and whatever consumes its channels. Reference the Null, not the source.
- Source CHOPs like
mouseIn,keyboardIn,audioIn,oscIn,midiInprefix/rename channels in non-obvious ways, which breaks naive references likeop('mouseIn1')['tx']. - The MCP cannot diagnose these failures from the source CHOP alone — the Null gives a stable, inspectable endpoint.
- After creating the Null, verify channel names (e.g.
list_children/ inspect it) before writing the downstream expression.
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.
- 6d ago First seen · 39 lines · 796 tokens per session scan A 390f753a1056
touchdesigner-mcp CLAUDE.md is an instructions file published in the GitHub repository mrinalghosh/touchdesigner-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 796 tokens to every session, about $0.0040 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.
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.
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.
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).
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).
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.
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.