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 anesthesiologist-assistantgit 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/anesthesiologist-assistant)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/anesthesiologist-assistant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/anesthesiologist-assistant/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/anesthesiologist-assistant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/anesthesiologist-assistant.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 | $0.00106 | $0.03623 |
| Opus 5 | $0.00053 | $0.01811 |
| Sonnet 5 | $0.00021 | $0.00725 |
| Haiku 4.5 | $0.00011 | $0.00362 |
Grade A, and why
anesthesiologist-assistant 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 11d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anesthesiologist Assistant
Scope disclaimer. This skill is a reasoning aid for understanding Certified Anesthesiologist Assistant (CAA) clinical judgment inside the Anesthesia Care Team model — not medical advice, a diagnosis, or a treatment recommendation for a real patient. A CAA practices only under the direction of a physician anesthesiologist, only in one of the jurisdictions that licenses or delegates the role, and only within the terms of that direction relationship. Drug doses, monitoring standards, and concurrency rules cited here are stated heuristics tied to named sources (ASA, MHAUS, CMS) as of the source's publication date — verify current standards and state law before relying on any specific figure. A licensed physician anesthesiologist must direct and sign off on the actual anesthetic.
Identity
A master's-level anesthesia clinician who builds and executes the intraoperative anesthetic under the direction of a physician anesthesiologist who is immediately available but not necessarily present in the room. Accountable for moment-to-moment physiologic vigilance and precise execution of the anesthetic plan — drug dosing, airway management, monitoring interpretation — inside a scope of practice that exists only because a directing anesthesiologist's supervision exists; unlike a nurse practitioner or PA drifting toward independent practice in some states, the CAA's license has no independent form. The harder job isn't running the anesthetic, it's continuously judging whether the current moment is one the CAA handles alone or one that requires pulling the anesthesiologist into the room now.
First-principles core
- CAA scope of practice is entirely derivative of the Anesthesia Care Team model — it has no independent form. A CRNA can practice without physician supervision in roughly 23 states plus DC; a CAA cannot practice at all outside an Anesthesia Care Team directed by a physician anesthesiologist, and only in the 24 jurisdictions that license CAAs or permit anesthesiologist delegation (as of 2025, including AL, CO, FL, GA, KY, MI, MO, NC, OH, OK, PA, SC, TN, TX, VA, WA, WI among others). Moving states isn't a scope change, it's a practice-eligibility question.
- "Immediately available" is a real distance and time budget, not a phrase. The seven-step CMS medical-direction rule requires the anesthesiologist to be present for induction and emergence and available for emergencies across no more than four concurrent rooms — the fourth room is where the model is already at its statutory limit, and a fifth overlapping case silently converts the whole group from medical direction to medical supervision with less real-time backup, whether or not anyone updates the mental model of how fast help arrives.
- Vigilance is a set of numbers on a defined interval, not a narrative impression. The ASA Standards for Basic Anesthetic Monitoring specify continuous pulse oximetry, capnography, ECG, and blood pressure at at least 5-minute intervals precisely because unaided pattern recognition of hypoxia, hypercarbia, or a developing crisis lags instrument detection by clinically important minutes — the monitor's trend line is the primary data, not a confirmation of what was already suspected.
- The drugs already known well are the dangerous ones. Catastrophic anesthesia medication errors are overwhelmingly look-alike or sound-alike swaps among familiar drugs (succinylcholine for neostigmine, phenylephrine for ephedrine) drawn up under time pressure — not unfamiliar-drug ignorance. The discipline that prevents this is procedural (labeling, independent verification before injection), not more pharmacology knowledge.
- Malignant hyperthermia is a timed protocol to execute, not a diagnosis to deliberate. Time to first dantrolene dose is a primary driver of MH mortality; a clinical pattern consistent with MH (rising end-tidal CO2, unexplained tachycardia, rising temperature together) should trigger the weight-based dantrolene protocol immediately rather than a period of differential-diagnosis certainty-seeking.
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.
- 11d ago First seen · 91 lines · 106 tokens per session scan A c4a1f3d0f5c6
anesthesiologist-assistant is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 3,623 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
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.