tdpilot-production

tdpilot-production is a skill for Claude Code from dreamrec/TDPilot. It costs 48 tokens per session (1,152 once invoked), scanned A, original, MIT.

A set of production-safety instructions for editing TouchDesigner projects through TDPilot, an assistant with tools for live visual projects.

In plain words
What is it for?
Use it for destructive, broad, performance-sensitive, or show-critical TouchDesigner changes that must be stable and safe.
Why use it?
It reduces the risk of damaging a show-critical project by requiring staged changes, rollback planning, performance checks, and evidence that protected output still works.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it for destructive, broad, performance-sensitive, or show-critical TouchDesigner changes that must be stable and safe.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dreamrec/tdpilot/tdpilot-production
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 dreamrec/TDPilot --skill tdpilot-production
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-production

README.md
[![agentmods](https://agentmods.dev/badge/skills/dreamrec/tdpilot/tdpilot-production/github.svg)](https://agentmods.dev/skills/dreamrec/tdpilot/tdpilot-production)
Your own site
<a href="https://agentmods.dev/skills/dreamrec/tdpilot/tdpilot-production"><img src="https://agentmods.dev/badge/skills/dreamrec/tdpilot/tdpilot-production/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 tdpilot-production

Your own site · 80×15
<a href="https://agentmods.dev/skills/dreamrec/tdpilot/tdpilot-production"><img src="https://agentmods.dev/badge/skills/dreamrec/tdpilot/tdpilot-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,152 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 $0.00048 $0.01152
Opus 5 $0.00024 $0.00576
Sonnet 5 $0.00010 $0.00230
Haiku 4.5 $0.00005 $0.00115

Measured 9d ago against content hash 840be5028fe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tdpilot-production 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 9d 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.

plugins/tdpilot/skills/tdpilot-production/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDPilot Production v2.4.1

Use this skill in addition to tdpilot-core when work is show-critical, performance-sensitive, destructive, broad in scope, or explicitly requested as stable, production-ready, or show-safe.

Core Rule

Protect the running project and its active output. Prove the target and preservation boundary, use the correct brain route, apply the smallest staged change, and accept it only when graph, runtime, visual, performance, and preservation checks pass.

Production Workflow

1. Scope and preflight

  • Inspect focus, exact target root, direct connections, active output, and protected paths. Use td_get_info/td_get_capabilities only when build or capability compatibility matters.
  • Read current errors and performance once for a baseline.
  • Batch independent reads with td_tool_batch; keep mutations transactional.
  • Record device, resolution, FPS, latency, and output-routing constraints.
  • Treat an ambiguous active route, missing external device, or unproven ownership boundary as a blocking question.

2. Choose the build route

  • One proven edit at a known path may use a typed primitive tool.
  • An exact compiler-backed pattern may use td_brain_plan.
  • Artistic, multi-domain, spatial, or implicit architecture goes directly through td_brain_ground → author → td_brain_propose.
  • Require complete intent coverage and concrete lowering for control/reference edges before execution. A partial plan is not a production fallback.

Recall compatible local techniques before taste-critical authoring. Memory and knowledge may inform a proposal, but only validated techniques or promoted traces may compile automatically.

3. Safety baseline

Brain execution already provides snapshot, undo, validation, and rollback; do not surround it with redundant manual wrappers. For direct primitive edits:

  • Snapshot before destructive or broad changes.
  • Start one named undo block around a coherent batch.
  • Set bounds before modifying show-sensitive numeric controls.
  • Keep the prior active path intact until a replacement is validated.

Read the full file on GitHub · 132 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. 9d ago First seen · 132 lines · 48 tokens per session scan A 840be5028fe8

Subscribe to this mod's changes

tdpilot-production is a skill published in the GitHub repository dreamrec/TDPilot (11 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,152 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-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-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-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