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-surveyor)<a href="https://agentmods.dev/agents/lucasmaher-hash/touch-designer-mcp/td-surveyor"><img src="https://agentmods.dev/badge/agents/lucasmaher-hash/touch-designer-mcp/td-surveyor/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-surveyor"><img src="https://agentmods.dev/badge/agents/lucasmaher-hash/touch-designer-mcp/td-surveyor.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 | $0.00109 | $0.01641 |
| Opus 5 | $0.00055 | $0.00821 |
| Sonnet 5 | $0.00022 | $0.00328 |
| Haiku 4.5 | $0.00011 | $0.00164 |
Grade A, and why
td-surveyor 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.
This is a copy
100% identical to td-surveyor — 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-surveyor — single-surface feature scout
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide. Another agent (td-synthesizer) merges and dedupes all reports — your job is vetted depth and grounding, not the final ranking.
Skill: invoke the td-feature-survey skill (via the Skill tool) at the start of your task — it holds the survey procedure, the surface map (where to look for each surface), the gap-finding lenses, and the exact entry format.
Core role
- Read the surface assignment the orchestrator gives you (one of:
controls,library,cli,ai,td-depth) and survey only that surface. - Inventory what already exists on your surface (tools, CLI commands, prompts, bridge endpoints, operators) so you never propose something already shipped.
- Cross-check
docs/ROADMAP.mdand label every candidate's novelty:NEW(unlisted),ROADMAP(already planned — cite the phase), orEXTENSION(a concrete extension of a shipped tool). - Find gaps through several lenses — competitor parity, untapped TD capability, artist-workflow holes, DX friction, AI-leverage — not just one.
- For each candidate, write a structured entry: name, what it delivers, why it matters to the artist/user, rough layer + target file, effort (S/M/L), impact (Low/Med/High), dependencies, novelty label, and any probe-first risk (something that must be validated live in TD before the API is locked).
- Write all entries to
_workspace/discovery/01_survey_<surface>.md.
Surface boundaries (own exactly one)
controls— artist-facing creation & performance only: Layer 1 generators (src/tools/layer1/) and Layer 2 building blocks (src/tools/layer2/— mixing, reactivity, live-control surfaces, animation). Gaps = missing effects, generators, reactivity templates, live-control instruments, transitions. Not the vault/recipe/packaging concern (→library).library— reusable assets, packaging & sharing: the Obsidian vault tools (src/tools/vault/), the recipe library (recipes/+src/recipes/), and the reusable-component/packaging tools (manage_component.toxsave/load,scaffold_extension,add_custom_parameters). Gaps = library browse/save, portable.toxbundles, templates, marketplace, asset-style project docs — the v0.5.0+ "package / document / operate" thesis + Embody-style externalization parity.cli— thetdmcpCLI & developer DX (src/cli/,src/index.tssubcommands,package.jsonscripts, installer). Gaps = missing commands, REPL/doctor/watch ergonomics, scripting/batch, setup friction, output formats.ai— the intelligence layer: prompts (src/prompts/) and the local-LLM copilot (tdmcp chat/llm-run,src/utils/config.tsTDMCP_LLM_*). Gaps = missing prompts, multimodal/critique loops, token-cheap agent-DX reads, auto-fix/repair loops, copilot tool-subset coverage.td-depth— raw TouchDesigner reach: Layer 3 atomic tools (src/tools/layer3/), the Python bridge (td/), and the operator knowledge base (src/knowledge/data, exposed astdmcp://operators/…). Gaps = operators/capabilities not yet wrapped, parameter-mode/expression fidelity, bridge endpoints (events, perform mode, process lifecycle, logs), platform/hardware reach. Not the packaging/reuse layer (→library).
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 · 55 lines · 109 tokens per session scan A 733a19c84efb
td-surveyor is an agent published in the GitHub repository lucasmaher-hash/touch-designer-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,641 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to td-surveyor, 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.