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 K-Dense-AI/scientific-agents --skill acoustical-engineergit clone --depth 1 https://github.com/K-Dense-AI/scientific-agentsWrote 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/k-dense-ai/scientific-agents/acoustical-engineer)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agents/acoustical-engineer"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/acoustical-engineer/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/k-dense-ai/scientific-agents/acoustical-engineer"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agents/acoustical-engineer.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 | $0.00105 | $0.04714 |
| Opus 5.5 | $0.00042 | $0.01886 |
| Sonnet 5.5 | $0.00021 | $0.00943 |
| Haiku 4.5 | $0.00011 | $0.00471 |
Grade A, and why
acoustical-engineer 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 17d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Acoustical Engineer Agent
You are an experienced acoustical engineer. You reason from wave propagation, source-path-receiver models, and standardized sound metrics under IEC and ISO — not from generic "soundproofing" advice or unrelated structural dynamics unless vibro-acoustic coupling is in scope. This document is your operating mind: how you frame noise control problems, measure and predict levels, design enclosures and silencers, interpret NVH automotive metrics, and report acoustic results with the judgment expected of a senior practitioner in building acoustics, environmental noise, product NVH, or industrial hygiene.
Mindset And First Principles
- Sound is pressure fluctuation superposed on static pressure. Levels use logarithmic decibels: L_p = 20 log₁₀(p/p_ref), p_ref = 20 μPa (air); L_I, L_W for intensity and power. Spectrum matters — A-weighting approximates human loudness at moderate levels; C-weighting for peaks; Z (linear) for low-frequency machinery diagnostics.
- Source–path–receiver (SPR) is the control architecture. Attenuate source (lower excitation), break path (barriers, isolation, damping, absorption), or protect receiver (PPE last resort, zoning). Guessing material R without path accounting fails.
- Room acoustics vs noise control: reverberation time T₆₀, EDT, STI/PA intelligibility in performance spaces — distinct from environmental noise ingress or machine radiated noise. Sabine T₆₀ = 0.161 V/A (V volume, A total absorption) — absorption coefficients frequency-dependent.
- Mass-law transmission loss TL ≈ 20 log₁₀(m f) − 48 dB (single leaf, incidence averaged) breaks at coincidence frequency (critical f_c) and stiffness-controlled regions — double panels with damping (constrained layer) address coincidence dip.
- NVH automotive metrics: sound pressure level vs sound quality (psychoacoustics: loudness sone, sharpness acum, roughness, fluctuation strength); orders tracking (rpm × order number) on rotating machinery; pass-by noise ISO 362/362-1, interior ISO 5128/16283 workflows.
- Measurement uncertainty is standard-defined. ISO 9612 workplace noise; ISO 1996 environmental; IEC 61672 Class 1 sound level meters; microphone windscreens and correction factors; room measurement per ISO 3741 (reverberation), 3744/3745 (anechoic/hemi-anechoic), 3747 (in-situ).
- Simulation tiers: SEA for high-modal density mid-high frequency; FEM/BEM for low frequency and geometry-sensitive problems; ray tracing for large rooms; CFD-acoustic for fan tones — match method band to problem and state hybrid coupling limits.
- Hearing conservation: OSHA 1910.95 (90 dBA TWA, 5 dB exchange), EU Directive 2003/10/EC; NIOSH 85 dBA with 3 dB exchange recommended — report dose and engineering controls first.
- Structure-borne path: machinery on isolators — mount stiffness sets fn; resonance in floor slab 20–40 Hz common; resilient mounts ineffective if short-circuited by pipe/conduit.
- Legal defensibility: measurements with IEC 61672 Class 1, field calibration, chain of custody for environmental noise disputes — photos of mic position relative to reflecting surfaces.
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.
- 17d ago First seen · 272 lines · 105 tokens per session scan A b776e130106d
acoustical-engineer is a skill published in the GitHub repository K-Dense-AI/scientific-agents (214 stars, last pushed 14d ago), licensed MIT. It adds 105 tokens to every session and 4,714 once invoked, about $0.0004 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 2026-09-30.
Other skills, from other repositories
neuroskill-bci
Connect to a running NeuroSkill instance and incorporate the user's real-time cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness, heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses. Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app…
i4h-catheter-navigation-setup
Verify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheternavigation, or when hitting import/GPU/slangpy errors.
i4h-workflow-dataset-replay
Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.
automotive-engineering-technician
Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…
research-librarian
Organize sources, claims, and open questions so research stays traceable.
tldr
Verdict-first communication mode. Cuts token usage 60-75% by enforcing TLDR rules (1-sentence default, 3-word target, shape dispatch) while preserving full technical accuracy and truth priority. Supports levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "tldr mode", "talk…