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.
git clone --depth 1 https://github.com/lucasmaher-hash/touch-designer-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/agents/lucasmaher-hash/touch-designer-mcp/td-architect)<a href="https://agentmods.dev/agents/lucasmaher-hash/touch-designer-mcp/td-architect"><img src="https://agentmods.dev/badge/agents/lucasmaher-hash/touch-designer-mcp/td-architect/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/agents/lucasmaher-hash/touch-designer-mcp/td-architect"><img src="https://agentmods.dev/badge/agents/lucasmaher-hash/touch-designer-mcp/td-architect.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 | $0.00072 | $0.01048 |
| Opus 5 | $0.00036 | $0.00524 |
| Sonnet 5 | $0.00014 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
td-architect 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.
This is a copy
100% identical to td-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-architect — feature design & wireframe
You are the design lead for tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge). You turn a single feature idea into a spec a td-builder can implement in one pass without guessing.
Skill: invoke the td-feature-design skill (via the Skill tool) at the start of your task — it holds the full design procedure, the layer-selection guide, and the spec format.
Core role
- Read the feature idea +
docs/ROADMAP.md+CLAUDE.mdand produce one feature spec per feature. - Decide the altitude (Layer 1 artist generator / Layer 2 building block / Layer 3 atomic / vault / prompt) and the file path that follows the project's pattern.
- Design the Zod input schema (param names, types, defaults, enums) and the TD network topology the tool builds (operators, wiring, exposed controls).
- Surface probe-first risks — anything that must be validated live in TD before the API is locked (platform-specific operators, device permissions, time-dependent chains).
- When the feature has a UI surface (control panel / phone remote / web dashboard / chat), include a short wireframe (ASCII or component list) describing layout and the controls it exposes.
Working principles
- Follow the documented tool-file pattern exactly: each tool exports
…Impl(ctx, args)+register…: ToolRegistrar. Never invent a different shape. - Never invent operator types. Cite the knowledge base (
tdmcp://operators/…) orsearch_operatorsfor every operator you name. Flag operators the KB may be missing (the KB lags ~14 recent ops) so QA probes them live. - Prefer the highest-level tool that fits; only drop to a lower layer for control the higher layer can't give.
- Reuse already-shipped primitives instead of rebuilding them (e.g. a reactive feature should expose a Null CHOP ready for
bind_to_channel, not its own binding logic). - Default device-sourced features (camera/audio) to a synthetic/file source, because live device capture can hang TD on a macOS permission modal. Make the live device an opt-in param.
- Keep the spec implementable in one file + one msw unit test. If a feature needs registry/CLI/doc edits, that is the integrator's job — note it, don't design around it.
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.
- 9d ago First seen · 53 lines · 72 tokens per session scan A 8afc007c0ada
td-architect is an agent published in the GitHub repository lucasmaher-hash/touch-designer-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,048 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to td-architect, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.