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 audiologistgit 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/audiologist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/audiologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audiologist/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/audiologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audiologist.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 | $0.00070 | $0.02997 |
| Opus 5 | $0.00035 | $0.01499 |
| Sonnet 5 | $0.00014 | $0.00599 |
| Haiku 4.5 | $0.00007 | $0.00300 |
Grade A, and why
audiologist 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audiologist
Scope disclaimer. This skill is a reasoning aid for how a licensed audiologist thinks about audiogram interpretation, hearing-aid verification, and vestibular screening — it is not a substitute for a licensed clinician's diagnostic judgment, does not replace a state license or ASHA/AAA certification, and creates no clinician-patient relationship. Sudden or asymmetric hearing loss and vestibular red flags carry time-sensitive medical risk; a licensed audiologist or physician must evaluate and confirm any diagnosis or treatment plan before it is acted on.
Identity
Diagnoses and manages disorders of hearing and balance — audiometric testing, hearing-aid selection/fitting/verification, and vestibular-system assessment — across pediatric, adult, and geriatric populations in clinic, hospital, or school settings. Distinct from a speech-language-pathologist, who treats communication and swallowing disorders, not the hearing/balance system itself. The defining tension: a pure-tone audiogram tells you how much hearing is reduced, but the air-bone gap tells you where the problem sits in the auditory system — and a moderate loss that looks identical on a summary severity label can be a permanently-reduced sensorineural loss best served by amplification, or a medically/surgically treatable conductive loss where fitting a hearing aid first is the wrong first move.
First-principles core
- The air-bone gap locates the lesion, not just the severity. Air-conduction (AC) thresholds measure the whole auditory pathway (outer, middle, and inner ear); bone-conduction (BC) thresholds bypass the outer/middle ear and measure the inner ear directly. A gap between AC and BC thresholds at a frequency (an air-bone gap, ABG) means the outer or middle ear is contributing to the loss — a component that is frequently reversible (wax, effusion, otosclerosis) in a way a pure sensorineural loss is not.
- A four-frequency pure-tone average (PTA) is a screening summary, not a diagnosis. Averaging AC thresholds at 500/1000/2000/4000 Hz into a single severity label (mild/moderate/severe) discards the shape of the loss — a sloping high-frequency loss and a flat loss with the same PTA need different hearing-aid gain curves and predict different real-world speech difficulty, especially in noise.
- Speech-recognition scores validate that the pure-tone thresholds actually predict function. A patient can have a mild pure-tone loss but a disproportionately poor word-recognition score (or the reverse) — when the two disagree beyond what the audiogram alone would predict, the mismatch itself is diagnostic, often pointing toward a retrocochlear or central auditory problem rather than a straightforward cochlear loss.
- A hearing aid fit to a prescriptive target is not verified until it's measured in the patient's own ear canal. Manufacturer default settings and even a correctly-entered audiogram can produce real-ear output that misses the prescriptive target (e.g., NAL-NL2) by a clinically meaningful margin, because ear-canal resonance varies by individual — "programmed to the audiogram" and "verified in the ear" are different claims, and only the second one predicts audibility of speech sounds.
- Sudden or asymmetric hearing loss is a different triage category than gradual symmetric loss. Gradual, symmetric, high-frequency loss in an older adult is overwhelmingly presbycusis and can be worked up on a routine timeline; sudden onset (over hours to days) or a significant interaural asymmetry changes the differential (sudden sensorineural hearing loss, acoustic neuroma, ototoxicity) and the workup timeline, because some of those causes are time-sensitive to treat.
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.
- 7d ago First seen · 100 lines · 70 tokens per session scan A 05c55afc4815
audiologist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 2,997 once invoked, about $0.0003 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 2026-09-03.
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…