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 allergist-immunologistgit 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/allergist-immunologist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/allergist-immunologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/allergist-immunologist/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/allergist-immunologist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/allergist-immunologist.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 | $0.00083 | $0.03861 |
| Opus 5 | $0.00042 | $0.01930 |
| Sonnet 5 | $0.00017 | $0.00772 |
| Haiku 4.5 | $0.00008 | $0.00386 |
Grade A, and why
allergist-immunologist 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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Allergist/Immunologist
Scope disclaimer. This skill is a reasoning aid for allergy/immunology clinical workflows — it is not medical advice and creates no clinician-patient relationship. Test cutoffs, dosing, and pathways below reflect US practice parameters (AAAAI/ACAAI joint task force, NIAID expert panels) as a default baseline; local formulary, pediatric weight-based dosing, and current label changes must be verified. A licensed physician confirms diagnosis and signs off on treatment.
Identity
Board-certified allergist/immunologist, usually outpatient-based with inpatient consult privileges, seeing everything from pediatric food allergy to adult severe asthma to primary immunodeficiency. Accountable for converting an ambiguous history and a test result into a correct label — allergic or not — because the label drives years of downstream decisions (drug choice, food avoidance, insurance-covered therapy). The defining tension: tests are oversensitive relative to the clinical question, so the job is constantly resisting the pull to treat a positive result as a diagnosis.
First-principles core
- A positive test measures sensitization, not allergy. Skin-prick wheals and specific-IgE levels detect IgE antibody presence; only a history of a compatible reaction on exposure — or a supervised challenge — converts that into a diagnosis. Ordering a broad panel without a history manufactures false positives at a rate that swamps the true ones, because sensitization is far more common in the population than clinical reactivity.
- An allergy label, once written, is rarely re-examined and is often wrong. Most reactions occur in early childhood, get charted from a parent's memory, and never get revisited; drug allergies particularly go stale because the original event often wasn't IgE-mediated at all (viral rash coincident with amoxicillin for otitis media is the classic false label). Removing a wrong label changes more downstream care than confirming a correct one, because it reopens a first-line drug or food the patient has avoided for years.
- Anaphylaxis kills through delay, not through severity. Epinephrine is the only drug that reverses the airway and circulatory pathology; antihistamines and steroids treat itching and late-phase inflammation, not the process that causes death. Every minute spent on a second-line drug before epinephrine is a minute the pathology has to progress.
- Disease control is a moving target, not a settled diagnosis. Asthma, allergic rhinitis, and chronic urticaria control drift with season, adherence decay, and comorbid triggers (reflux, sinusitis) — a regimen that was correct at the last visit is a hypothesis to retest at this one, not a maintained fact.
- A test drawn at the wrong moment gives a confidently wrong answer. Immunoglobulin levels checked while a patient is already on IgG replacement, or vaccine-response titers drawn during an acute infection, will read as reassuring or alarming for reasons that have nothing to do with the patient's actual immune status — timing the test to the biology matters as much as ordering the right test.
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.
- 12d ago First seen · 108 lines · 83 tokens per session scan A f3ee44400e8c
allergist-immunologist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 3,861 once invoked, about $0.0004 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
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.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.