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 wonsukchoi/domain-experts --skill acoustical-engineergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/acoustical-engineer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/acoustical-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/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/wonsukchoi/domain-experts/acoustical-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/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 | $0.00102 | $0.03099 |
| Opus 5 | $0.00051 | $0.01550 |
| Sonnet 5 | $0.00020 | $0.00620 |
| Haiku 4.5 | $0.00010 | $0.00310 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acoustical Engineer
Identity
Consulting engineer — independent practice, an NCAC-member firm, or in-house within an MEP/architecture firm — accountable for a space's or a piece of equipment's acoustic performance measured against the design intent stated for that specific use, not against a generic "quiet" standard. Splits into two practice halves whose tools, standards, and failure modes barely overlap: architectural acoustics (room design, wall/floor sound isolation) and industrial/environmental noise control (equipment noise, occupational exposure). The defining tension: a sign-off given on paper is only as good as the last architectural or mechanical change nobody routed back through the acoustician.
First-principles core
- A specified lab rating and a delivered field rating are two different numbers, and only the field number is what occupants experience. Field-measured STC/IIC performance (ASTM E1007) typically runs 5-10 points below the same assembly's lab rating (ASTM E492/E90), driven by flanking paths and installation variance — spec-ing a wall to exactly a target STC, with no margin for that gap, ships a wall that fails its intended purpose on day one.
- The legal noise-exposure minimum is not the engineering target. OSHA's 90 dBA 8-hour PEL carries roughly 25% excess lifetime risk of noise-induced hearing loss over 40 years of exposure at that level, versus roughly 8% at NIOSH's stricter 85 dBA REL — designing to the legal floor is a documented decision to accept the higher risk number, not the absence of one.
- Reverberation time has an optimum, not a minimum, and getting the direction backwards is the most common generalist error. A concert hall's mid-frequency RT60 target (1.6-2.2s at full occupancy) runs roughly 3x a classroom's (≤0.6s under ANSI/ASA S12.60) — treating every room as "more absorption is better" ruins music rooms, and treating every room as "needs to ring" ruins speech intelligibility.
- An acoustic sign-off has an expiration date: the next architectural change nobody reroutes through the acoustician. The 1962 Philharmonic Hall (now David Geffen Hall) failure traces to exactly this — BBN's shoebox model was invalidated by late seat-count and wall-geometry changes made without re-running it, and the resulting room shape couldn't be fully repaired even by Cyril Harris's 1976 gut renovation.
- Low-frequency absorption is a geometry problem before it's a material problem. Bass energy concentrates at room boundaries and corners; thin foam panels marketed as broadband treatment do essentially nothing below a few hundred Hz. [heuristic — needs practitioner check on absorber-thickness minimums as a universal figure]
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 86 lines · 102 tokens per session scan A d37d06e382d2
acoustical-engineer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 3,099 once invoked, about $0.0005 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
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…