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 Pantani/tdmcp --skill td-feature-designgit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/td-feature-design)<a href="https://agentmods.dev/skills/pantani/tdmcp/td-feature-design"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/td-feature-design/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/td-feature-design"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/td-feature-design.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 | $0.00110 | $0.00952 |
| Opus 5 | $0.00055 | $0.00476 |
| Sonnet 5 | $0.00022 | $0.00190 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
td-feature-design 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:
- td-feature-design — 100% identical, 0 lines differ
- td-feature-design — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
td-feature-design — turn an idea into an implementable spec
A spec is good when a builder can implement it in one file + one test without re-deciding anything. Aim for that bar.
Procedure
- Read the context first.
docs/ROADMAP.md(the idea is usually already scoped there),AGENTS.md(the conventions), and 1–2 neighbour tools in the targetsrc/tools/layer*/for the exact file pattern. - Pick the layer / altitude:
- Layer 1 (
src/tools/layer1/) — an artist tool that builds a whole wired+arranged network (goes throughorchestration.ts). - Layer 2 (
src/tools/layer2/) — a building block (connect, control panel, animate, external IO). - Layer 3 (
src/tools/layer3/) — atomic node CRUD / inspection / raw-Python escape hatch. src/tools/vault/— Obsidian-vault bridge. Asrc/prompts/entry — when the value is guidance to the model, not a deterministic build (multimodal / natural-language / critique ship as prompts).- Decide the file path now:
src/tools/layer<N>/<camelCaseName>.ts.
- Layer 1 (
- Design the Zod input schema — a param table: name, type, default, enum values, notes. Defaults matter: device-sourced inputs (camera/audio) default to a synthetic/file source (live device is opt-in) because device capture can hang TD on a macOS permission modal.
- Lay out the TD network topology — the operators it creates, how they wire, and the live controls it exposes. Reactive features must end on a Null CHOP ready for
bind_to_channel, reusing the shipped binding path instead of inventing one. Verify every operator type against the KB (tdmcp://operators/…orsearch_operators) — never invent a type. - Plan the bridge approach — almost always a Python payload via
buildPayloadScript(__PAYLOAD_B64__) executed through the client and parsed withparsePythonReport. Propose a new REST endpoint only when streaming or performance genuinely demands it. - Sketch a UI wireframe when the feature has a surface (control panel / control surface / phone remote / web dashboard / chat UI): an ASCII layout or component list naming each control and what parameter it drives.
- List probe-first risks — anything to validate live before locking the API: platform-specific operators (Syphon/Spout/NDI/Video-Stream-Out exist only on some OS/licenses), KB-missing operators (the KB lags ~14 recent ops; ~22 dir(td) names aren't createable), device permissions, and time-dependent chains that read 0 on a paused timeline.
- Write the test plan — what the offline msw unit test should assert (operators created, params set, wiring, the returned shape).
- Write integration notes — exactly which shared files the integrator must edit (
layer*/index.ts,src/cli/agent.tscommand name + flags, docs regenerate automatically).
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 · 37 lines · 110 tokens per session scan A d69122197019
td-feature-design is a skill published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 25d ago), licensed MIT. It adds 110 tokens to every session and 952 once invoked, about $0.0006 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.