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 skills add Pantani/tdmcp --skill tdmcp-raytk-integrationgit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/pantani/tdmcp/tdmcp-raytk-integration)<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-raytk-integration"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-raytk-integration/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.
<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-raytk-integration"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-raytk-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00213 | $0.02245 |
| Opus 5 | $0.00106 | $0.01123 |
| Sonnet 5 | $0.00043 | $0.00449 |
| Haiku 4.5 | $0.00021 | $0.00225 |
Grade A, and why
tdmcp-raytk-integration 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tdmcp-raytk-integration — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp-raytk-integration — orchestrator
Coordinate the dedicated team that integrates the external RayTK toolkit into
tdmcp as native operators. tdmcp already stages RayTK's .tox (the raytk manifest
in src/packages/registry.ts, via manage_packages) and ships its own GLSL
raymarching (createRaymarchScene/createSdfField/createSdfText). This harness
builds the missing layer: driving RayTK's ~300 ROPs as an editable node graph
(SDF primitives → combine → material → camera → render TOP) so the artist gets a
RayTK-native network, not another opaque GLSL string. The GLSL tools stay
complementary — never overwrite or shadow them.
Execution mode
Sub-agents, not TeamCreate (this repo's convention). Hybrid:
| Phase | Mode | Reason |
|---|---|---|
| Map | raytk-cartographer sub-agent |
external toolkit facts must be researched + cited before design |
| Plan | raytk-integration-lead (or local lead) |
dependency-order the waves, set write scopes |
| Build | parallel td-builder sub-agents (disjoint new files) |
one ROP tool + msw test each |
| Bridge | tdmcp-bridge-engineer, sequential |
only if exec→REST is justified; bridge slices share files |
| Integrate/docs | raytk-integration-lead single-writer |
registries, CLI, registry manifest, recipes, docs are shared |
| QA/fix | td-qa fan-in |
offline gates + live TD PASS/UNVERIFIED accounting |
Spawned agents use the inherited model unless the user asks otherwise.
Agent roster
| Agent | Role | Skills | Output |
|---|---|---|---|
raytk-cartographer |
map RayTK release, TD version gate, ROP taxonomy, wiring mechanism | web research | _workspace/raytk-integration/01_map.md |
raytk-integration-lead |
wave plan, briefs, single-writer integration, live validation | this skill, td-feature-integrate |
_workspace/raytk-integration/00_plan.md + final report |
td-architect |
Layer 1 scene spec (schema, topology, test plan) | td-feature-design |
_workspace/raytk-integration/spec_*.md |
td-builder |
one isolated ROP/scene tool file + msw test | td-feature-build |
new files only |
tdmcp-bridge-engineer |
REST endpoint + client + validator, only if needed | tdmcp-bridge-endpoint |
bridge slice |
td-qa |
gates, boundary QA, live TD validation | td-feature-qa |
_workspace/raytk-integration/04_qa.md |
td-releaser |
CHANGELOG/version/tag — only when user asks to ship | td-feature-release |
release commit |
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.
- 7d ago First seen · 153 lines · 213 tokens per session scan A d46ef3b30704
tdmcp-raytk-integration is a skill published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 25d ago), licensed MIT. It adds 213 tokens to every session and 2,245 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
popx-touchdesigner
Local POPX knowledge base and workflow for TouchDesigner. Use when the user mentions POPX, popsextension, POPX examples, POPX operators, or wants to build, inspect, explain, debug, or modify POPX-based setups in TouchDesigner using the bundled POPX reference corpus and live example loader when available.
tdpilot-core
Core patching discipline for TDPilot v2.4.1 — the AI assistant inside TouchDesigner. Use for all work through the td MCP tools: routing intent, inspecting live state, making safe edits, validating results, and recalling or learning local techniques.
tdpilot-production
Production-grade TouchDesigner MCP workflow for TDPilot v2.4.1 (114 tools): show-safe routing, bounded inspection, staged transactions, rollback, performance checks, preservation assertions, and evidence-based handoff.
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.