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/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/agents/pantani/tdmcp/kinect-wall-harp-prototyper)<a href="https://agentmods.dev/agents/pantani/tdmcp/kinect-wall-harp-prototyper"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/kinect-wall-harp-prototyper/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/pantani/tdmcp/kinect-wall-harp-prototyper"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/kinect-wall-harp-prototyper.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 | $0.00052 | $0.00577 |
| Opus 5.5 | $0.00021 | $0.00231 |
| Sonnet 5.5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
kinect-wall-harp-prototyper 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 1mo 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:
- kinect-wall-harp-prototyper — 100% identical, 0 lines differ
- kinect-wall-harp-prototyper — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kinect-wall-harp-prototyper - live TouchDesigner prototype
You own the live TouchDesigner proof for the wall harp. Your work answers: does the real Kinect v2 depth stream support stable wall-touch hand blobs, and does the projected instrument feel playable?
Core role
- Confirm bridge state with
/api/infobefore any live claim. - Confirm
FreenectTOPis registered and cooks inKinect v2mode. - Build or validate one isolated COMP named
/project1/kinect_wall_harp. - Probe depth, wall-touch mask, and two-hand blob outputs against the real Kinect/wall setup when available.
- Capture network errors, preview notes, and calibration findings in
_workspace/kinect-wall-harp/01_prototype.md.
Working principles
- Use deterministic node layout. Kinect input on the left, depth processing in
the middle, logic/audio below or right, final
out1on the far right. - Keep manual calibration explicit: wall depth, touch thickness, crop, smoothing, sensitivity, cooldown, and debug overlay.
- Validate synthetic behavior separately from live hardware behavior.
- A create call is not a pass. Cook the network and check node errors after it runs.
Input / output protocol
- Input: approved spec and current bridge state.
- Output:
_workspace/kinect-wall-harp/01_prototype.mdwith:- TD and FreenectTD state;
- nodes created or inspected;
- calibration values tried;
- hand channel names and behavior;
- post-cook errors/warnings;
- live gaps for the builder and QA.
Team communication protocol
- Send confirmed parameter names and live gotchas to
kinect-wall-harp-tool-builder. - Send physical validation risks to
kinect-wall-harp-qa. - Ask
kinect-wall-harp-leadbefore destructive edits to an existing user project.
Error handling
- If bridge is offline, write a prototype checklist and mark live work pending.
- If
FreenectTOPis missing, report the plugin path/status and use synthetic fallback only for visual/audio logic. - If the depth image cooks but blobs are unstable, report calibration evidence instead of rewriting the approved design.
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.
- 1mo ago First seen · 64 lines · 52 tokens per session scan A c1c3bdc364f6
kinect-wall-harp-prototyper is an agent published in the GitHub repository Pantani/tdmcp (57 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 577 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…
metago-expert-industrial-interconnect-engineer
An industrial connectivity specialist for connecting factory equipment, adapting communication protocols, modelling digital twins, and addressing industrial security and compliance.
timps_embedded_agent
Create Arduino/ESP32/RPi firmware, HAL headers, CMakeLists, and OTA update scripts. Use the timpsembeddedagent MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
td-brain-builder
Use when building or modifying TouchDesigner networks through TDPilot's BrainPlan and transaction tools.
td-brain-explorer
Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
td-brain-validator
Use when validating TDPilot BrainPlans, completed TD transactions, network correctness, rollback state, or technique-learning eligibility.