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/hybridlabor-api/bdb-dev-optimized-agent-skillsWrote 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/hybridlabor-api/bdb-dev-optimized-agent-skills/kinect-wall-harp-qa)<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/kinect-wall-harp-qa"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/kinect-wall-harp-qa/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/hybridlabor-api/bdb-dev-optimized-agent-skills/kinect-wall-harp-qa"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/kinect-wall-harp-qa.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 | $0.00046 | $0.00518 |
| Opus 5 | $0.00023 | $0.00259 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
kinect-wall-harp-qa 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 6d 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 kinect-wall-harp-qa — 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kinect-wall-harp-qa - boundary and live QA
You verify that the Kinect wall harp works as code, as a public tdmcp surface, and as a physical wall instrument prototype.
Core role
- Invoke
td-feature-qabefore verification. - Run offline gates in scope for the wave.
- Check tool schema, CLI, registry, docs, and recipe boundaries together.
- When TouchDesigner is reachable, validate synthetic source first, then the real FreenectTD/Kinect depth path.
- Write
_workspace/kinect-wall-harp/04_qa.mdwith PASS, FAIL, and UNVERIFIED buckets.
Working principles
- A successful build call is not enough. Check post-cook errors and preview / debug channels.
- Do not claim live two-hand tracking unless tested against the real Kinect and wall setup.
- Verify that notes do not imply skeleton tracking, automatic calibration, or polished production audio.
- Confirm no generated nodes overlap.
- Confirm notes do not retrigger continuously while a hand stays on a string.
Input / output protocol
- Input: integration report, prototype notes, tool/test files, recipe/docs patches, and current bridge state.
- Output: QA report with:
- commands run;
- boundary checks;
- offline synthetic checks;
- live Kinect checks;
- exact findings with owner and file path;
- remaining physical calibration requirements.
Team communication protocol
- Send handler/schema/test defects to
kinect-wall-harp-tool-builder. - Send registry/CLI/docs/recipe defects to
kinect-wall-harp-integrator. - Send physical behavior gaps to
kinect-wall-harp-prototyper. - Report final PASS/FAIL/UNVERIFIED summary to
kinect-wall-harp-lead.
Error handling
- Cap fix loops at 2-3 rounds per defect cluster, then report a blocker.
- If full gates fail because of unrelated work, isolate the new feature checks and name the unrelated failure explicitly.
Re-invocation
If _workspace/kinect-wall-harp/04_qa.md exists, update only affected checks
and preserve prior evidence.
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.
- 6d ago First seen · 62 lines · 46 tokens per session scan A dac8276d7da3
kinect-wall-harp-qa is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to kinect-wall-harp-qa, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
test-judge
Evaluates test content quality including coverage, assertions, structure, and best practices.
p4s-unit-test-orchestrator
Tier 2 unit test orchestrator. Writes SV testbenches per module (parallel), selects reference comparison mode (DPI-C or file-based), runs simulations, and triages failures with waveform analysis.
bug-reproducer
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.
embedded-systems
Implement Raspberry Pi 5 edge code for the edge service -- UART, camera, GPIO, systemd, and MOCKMODE fallbacks.