td-feature-survey

td-feature-survey is a skill for Claude Code, Codex from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 96 tokens per session (1,925 once invoked), scanned A, a copy of td-feature-survey, Apache-2.0.

A feature-research helper for TouchDesigner MCP (tdmcp), a tool for controlling TouchDesigner through an AI assistant. It surveys one area of the project and lists possible new features after checking what already exists and what is planned.

In plain words
What is it for?
Use it to review artist controls, the library, command-line tools, AI features, or TouchDesigner-specific capabilities.
Why use it?
It reduces duplicate ideas and keeps feature proposals grounded in the current code and roadmap.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to review artist controls, the library, command-line tools, AI features, or TouchDesigner-specific capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey
Install

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.

Any agent
npx skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill td-feature-survey
Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for td-feature-survey

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey/github.svg)](https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey)
Your own site
<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey/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.

agentmods 80×15 button for td-feature-survey

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/td-feature-survey.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.01925
Opus 5 $0.00048 $0.00962
Sonnet 5 $0.00019 $0.00385
Haiku 4.5 $0.00010 $0.00193

Measured 10d ago against content hash dd68df173187, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

td-feature-survey 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.

Origin

This is a copy

100% identical to td-feature-survey — 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.

mcps/tdmcp/.agents/skills/td-feature-survey/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

td-feature-survey — scout one surface for new features

You are surveying one assigned surface of tdmcp and returning a grounded, generous list of features it could gain. Breadth + grounding is the goal; the td-synthesizer prunes and ranks later. Work the surface methodically so you neither miss obvious gaps nor re-propose shipped tools.

Procedure

1. Confirm the surface

Your assignment is one of controls, library, cli, ai, td-depth. Survey only that surface. If you spot a strong idea on another surface, drop it in a one-line "cross-surface" footnote — don't fully work it up (its owner will).

2. Inventory what already exists

Read your surface's source (map below) and list what ships today. You cannot propose something that already exists, so build the "exists" set first. For tools, the registry under src/tools/ is authoritative; for CLI, src/cli/agent.ts; for prompts, src/prompts/; for operators, the KB.

3. Roadmap pass

Read docs/ROADMAP.md. Note every item on your surface that is shipped (☑), in progress (◐), or planned (☐ — Phase 13 / "deferred to v0.6.0+"). You will label candidates against this.

4. Gap-finding lenses

Run every candidate idea through these lenses — a good survey uses all of them, not just one:

Lens Question Where it bites for tdmcp
Competitor parity What do 8beeeaaat / Embody / dotsimulate LOPs have that we don't? network-as-JSON round-trip, token-cheap reads, annotations, perform mode
Untapped TD capability Which TD operators / Python APIs / bridge powers aren't wrapped yet? operators absent from the create-able set; bridge endpoints (logs, process, events)
Artist-workflow hole What's painful or missing in a real live show? the VJ/live thesis — audio/beat/camera reactivity, recovery, hands-free, output
DX / token cost What makes an agent slow, expensive, or error-prone here? compact reads, batch ops, surgical edits, diagnostics
AI leverage What could the model do that no prompt/tool exposes? multimodal critique, repair loops, set planning, project explain
Polish / robustness What breaks trust at the edges? export fidelity, safety/panic, portable bundles, validation

Read the full file on GitHub · 81 lines

Changes

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.

  1. 10d ago First seen · 81 lines · 96 tokens per session scan A dd68df173187

Subscribe to this mod's changes

td-feature-survey is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,925 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-feature-survey, differing in 0 lines, and is treated as a copy.