TDPilot: Skill for Claude Code

.agents/skills/tdpilot-brain-validator/SKILL.md

tdpilot-brain-validator is a skill for Claude Code from dreamrec/TDPilot. It costs 31 tokens per session (700 once invoked), scanned A, original, MIT.

A strict checking skill for TouchDesigner plans, changes, and node networks. TouchDesigner is a visual programming tool for interactive graphics and multimedia.

In plain words
What is it for?
Use it after planning or applying changes to verify operators, names, inputs, feedback loops, render pipelines, errors, rollback state, and basic visual correctness.
Why use it?
It checks actual structure, connections, runtime health, and visual results instead of trusting a success message alone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

This is dreamrec/TDPilot's own configuration. It tells Claude Code how to work on TDPilot 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 TDPilot configures →

Part of the tdpilot plugin — 8 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to dreamrec/TDPilot. 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/dreamrec/TDPilot/main/.agents/skills/tdpilot-brain-validator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dreamrec/TDPilot

Made for: Claude Code.

Or install tdpilot, the plugin that ships this one along with the rest of its 8 skills, 6 commands, 4 agents, 4 hooks, 1 MCP server.

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 tdpilot-brain-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/dreamrec/tdpilot/tdpilot-brain-validator.svg)](https://agentmods.dev/skills/dreamrec/tdpilot/tdpilot-brain-validator)
Your own site
<a href="https://agentmods.dev/skills/dreamrec/tdpilot/tdpilot-brain-validator"><img src="https://agentmods.dev/badge/skills/dreamrec/tdpilot/tdpilot-brain-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 700 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 $0.00031 $0.00700
Opus 5 $0.00015 $0.00350
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 7d ago against content hash bfd3aca52e2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tdpilot-brain-validator 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 7d 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.

.agents/skills/tdpilot-brain-validator/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDPilot Brain Validator

Use this skill after td_brain_plan, after td_brain_execute, or whenever the user asks whether a TouchDesigner network is correct.

Validator Posture

Be strict and evidence-based. A network is not correct just because tools returned success. It must match the concept, cook cleanly, and satisfy cheap visual sanity checks.

Core Rule

Do not approve correctness from a status flag alone. Validate concept, structure, runtime health, visual metrics, rollback state, and learning eligibility.

Validation Checklist

  • Plan integrity:

    • BrainPlan has no blocked_questions.
    • Concept graph edges reference real concept nodes.
    • Patch operations are dependency ordered and under max_ops.
  • TD grounding:

    • Operator types exist in the live TD family list.
    • Names do not conflict with existing nodes unless the plan explicitly handles it.
    • Parameters are valid for their operator cards or docsbrain evidence.
  • Structural checks:

    • Required inputs are connected.
    • Feedback loops contain a safe delay/feedback operator and level control.
    • Render pipelines have camera, geometry, material, light or explicit no-light design, render TOP, and output TOP.
    • Audio-reactive networks contain a CHOP source, analysis stage, modulation mapping, and visual target.
    • POP/POPx networks expose finite bounds and do not leave particle output detached.
    • GLSL networks expose shader source, compile state, uniforms, and output path.
    • Panel UI networks have callbacks/custom parameters wired to actual targets.
  • Runtime checks:

    • td_get_errors has no critical unacknowledged errors.
    • td_cooking_info or transaction validation reports acceptable cook health.
    • Parameter readback confirms important values were applied.
    • Optional visual metrics are plausible: luminance not black/white locked, alpha coverage nonzero, entropy above trivial threshold, frame delta present for animated outputs, POP bounds finite.

Severity

  • critical: broken network, failed rollback, missing required operator, hard TD error.
  • error: concept cannot be considered complete, output is absent, compile/cook failure.
  • warning: risky default, weak visual metric, missing optional evidence.
  • info: useful trace detail that does not affect pass/fail.

Read the full file on GitHub · 74 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. 7d ago First seen · 74 lines · 31 tokens per session scan A bfd3aca52e2f

Subscribe to this mod's changes

tdpilot-brain-validator is a skill published in the GitHub repository dreamrec/TDPilot (11 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 700 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

tdmcp-pipeline

Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…

Pantani/tdmcp · 128 tokens

td-trend-scout

Scout ONE external surface of the TouchDesigner community for what's HYPED in 2025-2026 that could become a tdmcp tool. Use when a td-trend-scout sub-agent is assigned a surface (community-showcase, tutorials, generative-ai, hardware-interactive, or vfx-aesthetics) during the tdmcp-hype-scout harness — produces…

Pantani/tdmcp · 120 tokens

tdmcp-kinect-wall-harp

Orchestrates the dedicated Kinect wall harp implementation team. Use whenever the user asks to build, implement, continue, fix, QA, document, or ship the Kinect wall harp, Kinect v2 wall-depth harp, FreenectTD depth-blob hand tracking, projected wall strings, pluck synth harp, or this feature's Layer 1…

Pantani/tdmcp · 97 tokens

tdmcp-raytk-integration

Plan and implement native RayTK (t3kt/raytk) raymarching/SDF toolkit integration into tdmcp — beyond the existing package-manager staging, into AI-driven RayTK operator (ROP) node graphs. Use whenever the user wants to build, plan, design, implement, continue, fix, QA, or ship RayTK support: create/wire RayTK ROPs, a…

Pantani/tdmcp · 213 tokens

tdmcp-artist-workflows

Build and refine TouchDesigner projects with tdmcp using context-first, visible, reversible workflows.

Pantani/tdmcp · 27 tokens

p5js

Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.

mateaix/mateclaw · 20 tokens