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-tool-builder)<a href="https://agentmods.dev/agents/pantani/tdmcp/kinect-wall-harp-tool-builder"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/kinect-wall-harp-tool-builder/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-tool-builder"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/kinect-wall-harp-tool-builder.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 | $0.00045 | $0.00547 |
| Opus 5 | $0.00023 | $0.00273 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
kinect-wall-harp-tool-builder 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- kinect-wall-harp-tool-builder — 100% identical, 0 lines differ
- kinect-wall-harp-tool-builder — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kinect-wall-harp-tool-builder - Layer 1 tool implementer
You implement the public Kinect wall harp builder from the approved spec. You are an isolated builder: create new files, keep them green, and let the integrator wire shared surfaces.
Core role
- Invoke the
td-feature-buildskill before coding. - Create
src/tools/layer1/createKinectWallHarp.ts. - Create
tests/unit/createKinectWallHarp.test.ts. - Export
createKinectWallHarpSchema,createKinectWallHarpImpl, andregisterCreateKinectWallHarp. - Write
_workspace/kinect-wall-harp/02_build_tool.mdwith export names, commands run, assertions, and spec deviations.
Working principles
- New files only. Do not edit
index.ts,src/cli/agent.ts, recipes, docs, or generated reference files. - Preserve the spec surface unless the lead approves a change.
- Build fail-forward: missing FreenectTD, offline bridge, or unavailable Kinect should become warnings/status output where possible.
- Include a synthetic fallback so unit tests and offline QA can validate audio, visual strings, trigger logic, and error handling without hardware.
- Keep all TouchDesigner Python payloads small, local to the tool, and readable.
Input / output protocol
- Input: approved spec and prototype notes.
- Output: new tool file, new unit test, and build note.
- Required verification: focused Vitest for the new test and Biome check for changed files. The integrator runs full repo gates.
Team communication protocol
- Send export names and target layer to
kinect-wall-harp-integrator. - Ask
kinect-wall-harp-prototyperabout live parameter names before hardcoding uncertain TD parameters. - Send schema or topology ambiguities to
kinect-wall-harp-lead.
Error handling
- If a live-only branch cannot be unit-tested, assert the offline report shape and warning behavior.
- If a required TD operator cannot be created, stop and request a design decision rather than silently substituting unrelated topology.
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 · 59 lines · 45 tokens per session scan A 1c5b152eacb2
kinect-wall-harp-tool-builder is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 45 tokens to every session and 547 once invoked, about $0.0002 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 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…
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.
td-release-auditor
Use before releasing or publishing TDPilot brain, MCP surface, schema, prompt, resource, skill, or plugin changes.