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 axysar/touchdesigner-agent-mcp --skill td-guidegit clone --depth 1 https://github.com/axysar/touchdesigner-agent-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/skills/axysar/touchdesigner-agent-mcp/td-guide)<a href="https://agentmods.dev/skills/axysar/touchdesigner-agent-mcp/td-guide"><img src="https://agentmods.dev/badge/skills/axysar/touchdesigner-agent-mcp/td-guide/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/axysar/touchdesigner-agent-mcp/td-guide"><img src="https://agentmods.dev/badge/skills/axysar/touchdesigner-agent-mcp/td-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.01309 |
| Opus 5 | $0.00030 | $0.00655 |
| Sonnet 5 | $0.00012 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
td-guide 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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-guide
You are about to modify a TouchDesigner network via the touchdesigner-agent-mcp tools.
Read this before you mutate anything.
Rule 1 — Your prior knowledge of TouchDesigner parameter names is unreliable
Assume your memory of TD parameter names is completely unreliable. They frequently differ from the visible label, and common-sense guesses are usually wrong:
- A Sphere SOP's radius is
radx/rady/radz, notradius. - A Noise TOP's amplitude is
amp, notamplitude. - Translate is
tx/ty/tz; rotaterx/ry/rz; scalesx/sy/sz.
Before setting any parameter on an operator you just created or have not
inspected, call get_td_node_parameters (or, inside execute_python_script,
tdapi.GetParameterList(op_type)). Read the real names back, then update.
update_td_node_parameters reports unknown names in its failed list instead
of raising — a "success" where everything landed in failed means your names
were wrong.
Rule 2 — See the network, don't guess at it
| Question | Tool |
|---|---|
| Where is the user looking? | td_pane |
| What is selected right now? | td_selection |
| What does this TOP actually output? | td_viewport with target=<top path> |
| What does the editor pane look like? | td_viewport with target='pane' |
| What children does this op have? | get_td_nodes |
| What parameters does this node hold? | get_td_node_parameters |
| Are there errors here or below? | get_td_node_errors |
Follow any non-trivial mutation with a td_viewport or get_td_node_errors
check — confirm what happened instead of asserting it.
Rule 3 — Nested baseCOMP cooking is a landmine
Operators inside a nested baseCOMP do not always re-cook when referenced
indirectly; the cached buffer goes stale. This is a known TouchDesigner gotcha.
If an edit inside a base/tox COMP looks wrong, call td_cook on the parent
COMP before debugging anything else:
td_cook(path='/project1/base1', recurse=true)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 117 lines · 61 tokens per session scan A dd833e4b56ea
td-guide is a skill published in the GitHub repository axysar/touchdesigner-agent-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 1,309 once invoked, about $0.0003 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.