Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Pantani/tdmcpnpx agentmods add skills/pantani/tdmcp/tdmcp-tool-builderWrote 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-tool-builder)<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-tool-builder"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-tool-builder/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-tool-builder"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-tool-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 189 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 225 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 192 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00144 | $0.03085 |
| Opus 5 | $0.00072 | $0.01543 |
| Sonnet 5 | $0.00029 | $0.00617 |
| Haiku 4.5 | $0.00014 | $0.00309 |
Grade A, and why
tdmcp-tool-builder 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 10d 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
2 near-identical copies found in the catalogue:
- tdmcp-tool-builder — 100% identical, 0 lines differ
- tdmcp-tool-builder — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp-tool-builder
You build one new tdmcp tool, end to end, matching the repo so closely a reviewer cannot tell which files are new. tdmcp is a TouchDesigner MCP server: a Node/TS server (this repo) drives a Python bridge running inside TouchDesigner. A "tool" is a TS handler that the AI can call; most tools do their work by sending one Python script to the bridge and parsing a JSON report back.
The canonical template is src/tools/layer2/manageComponent.ts. Read it
first, every time. Copy its shape exactly. The rules below explain why each
piece exists so you make the right call on edge cases.
The contract: one file, two exports (+ schema)
Every tool file exports three things and nothing surprising:
export const xSchema = z.object({ … })— the Zod input schema. Each field gets a.describe()written for an AI caller (say what it does and the units).export async function xImpl(ctx: ToolContext, args): Promise<CallToolResult>— the pure, testable handler. It takes the injectedToolContext({ client, knowledge, recipes, logger, vault?, allowRawPython }) and the validated args. All TD work goes throughctx.client. Unit tests call this directly with a mocked client — so it must never read globals or env directly.export const registerX: ToolRegistrar = (server, ctx) => server.registerTool( name, { title, description, inputSchema: xSchema.shape, annotations }, (args) => xImpl(ctx, args)).
Types come from ../types.js (ToolContext, ToolRegistrar). The name is
snake_case (add_custom_parameters); the file is camelCase
(addCustomParameters.ts); the registrar is registerAddCustomParameters.
annotations describe side effects for the client UI. Mutating builders use
{ readOnlyHint: false, destructiveHint: false, openWorldHint: true }. Pure read
tools use { readOnlyHint: true, openWorldHint: true }. A tool that can wipe data
sets destructiveHint: true.
Read tools: prefer structuredResult + outputSchema
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.
- 10d ago First seen · 230 lines · 144 tokens per session scan A 1f34a1c9e395
tdmcp-tool-builder is a skill published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 25d ago), licensed MIT. It adds 144 tokens to every session and 3,085 once invoked, about $0.0007 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 2026-08-30.
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.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.