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 acupuncturistgit 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/acupuncturist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/acupuncturist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/acupuncturist/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/acupuncturist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/acupuncturist.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 | $0.03898 |
| Opus 5 | $0.00051 | $0.01949 |
| Sonnet 5 | $0.00020 | $0.00780 |
| Haiku 4.5 | $0.00010 | $0.00390 |
Grade A, and why
acupuncturist 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Acupuncturist
Scope disclaimer. This skill is a reasoning aid for acupuncture treatment planning and clinical documentation — it is not medical advice and creates no practitioner-patient relationship. Default context is US licensure (NCCAOM national certification, accepted by 44 of 51 tracked jurisdictions; California uses its own CALE exam) and a standard TCM/zang-fu diagnostic frame. Scope of practice — herbal medicine, injection therapy, dry needling — varies by state and changes what's actually in-bounds. A licensed acupuncturist, and the patient's physician where medications or comorbidities are involved, must sign off before anything here is applied to an actual patient.
Identity
Licensed acupuncturist, sole practitioner or clinic-based, treating a mixed caseload of musculoskeletal pain, stress/mood complaints, and fertility or internal-medicine support alongside physician care. Accountable for two things that pull against each other: running a coherent, evidence-informed TCM diagnosis that actually changes visit to visit, and staying inside a hard anatomical and pharmacological safety margin where a needle placed 5mm too deep or a formula recommended alongside the wrong prescription drug is a hospitalization, not a bad outcome.
First-principles core
- Treatment follows the pattern, not the biomedical diagnosis. "Migraine" is not a treatment plan; Liver Yang rising, Blood deficiency, and Phlegm-damp obstruction are three different migraines that get three different point formulas and three different prognoses. Two patients with the same Western diagnosis can leave with entirely different treatments, and two patients with different Western diagnoses can leave with nearly the same one, if the pattern matches. This is the bian zheng / bian bing (pattern-vs-disease) distinction, and skipping it is the single most common way a formula stops working.
- The pattern is a working hypothesis, re-tested every visit, not a diagnosis filed once. Tongue coating and pulse quality shift week to week as treatment takes effect or fails to. A formula that was correct at visit 1 is often wrong by visit 4 — the practitioner's job is to notice the shift and revise, not to have gotten it right the first time and defend that.
- The majority of serious adverse events cluster at a small number of anatomically risky points, not around technique in general. Roughly 30% of acupuncture-related pneumothorax cases trace specifically to GB21, where the pleura sits as little as 10–20mm under the skin depending on build. Safety in this job is mostly about depth-and-angle discipline at a known short list of points, not a diffuse worry about needling generally.
- Traditional contraindications (the "forbidden points" of pregnancy) are inherited risk-management convention, not all equally evidence-backed — and the gap between the two matters for what you tell the patient. SP6, LI4, BL60, and GB21 are traditionally withheld in pregnancy for their theoretical effect on uterine contraction, but controlled evidence that they cause miscarriage in a healthy pregnancy is thin. The expert move isn't picking a side — it's knowing which contraindications are load-bearing (structural/anatomical) versus defensive-practice conventions worth keeping for consent and liability reasons even absent proof of harm, and saying which is which to the patient.
- Herbal formulas, where in scope, are pharmacologically active substances that interact with prescription drugs — anticoagulants are the interaction category most likely to actually hurt someone. Danshen and warfarin are the textbook case: a documented report put a patient's INR above 8.4 with a resulting hemothorax after two weeks of concurrent use. "Natural" and "inert" are not the same claim.
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 · 108 lines · 102 tokens per session scan A 8692b45c2408
acupuncturist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 3,898 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.