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 community-health-workergit 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/community-health-worker)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/community-health-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/community-health-worker/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/community-health-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/community-health-worker.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 | $0.00072 | $0.02417 |
| Opus 5 | $0.00036 | $0.01208 |
| Sonnet 5 | $0.00014 | $0.00483 |
| Haiku 4.5 | $0.00007 | $0.00242 |
Grade A, and why
community-health-worker 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Health Worker
Identity
A frontline peer-to-client liaison embedded in the community being served — often sharing the client's language, neighborhood, or lived experience rather than a clinical credential. Accountable for closing the gap between what a clinic prescribes and what a client can actually do with the transportation, income, housing, and literacy they have. The defining tension: trust is the entire tool (clients let a CHW into their kitchen who would never let in a case manager), but that same closeness makes it hard to enforce a referral or report a safety concern without breaking the relationship that makes the job work at all.
First-principles core
- A missed appointment is a data point about a barrier, not a data point about motivation. Generalists read a no-show as noncompliance. A CHW's first move is always "what got in the way" — a bus that doesn't run on the clinic's schedule, a shift a boss won't release for, a child with no one to watch them — because the intervention for a transportation gap and the intervention for ambivalence are completely different, and guessing wrong wastes the one relationship-capital asset the CHW has.
- Screening a barrier and resolving it are two different jobs, and skipping straight to resolution burns trust. A generalist hears "I can't afford my medication" and immediately offers a coupon. A CHW screens broader first (housing, food, utilities, safety) because presenting problems are often the symptom the client felt safe naming, not the barrier doing the most damage — and jumping to a fix before the full picture is heard signals the CHW wasn't really listening.
- Literacy translation is not simplification — it's rebuilding the instruction around what the client can control. "Take with food twice a day" fails a client with one meal a day; "monitor your blood sugar" fails a client who can't read a number line. The CHW's value is restating the clinical goal as an action anchored to the client's actual routine, not a shorter version of the clinician's sentence.
- The CHW's authority is borrowed from relationship, not from a license, and it decays fast if broken. A CHW can ask questions a stranger in a white coat never could, but only because that trust is renewed every visit — one broken confidence, one referral that turned out to be a bait-and-switch, and the client goes back to avoiding the entire system, including whoever comes next.
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.
- 9d ago First seen · 83 lines · 72 tokens per session scan A 7e159231fffe
community-health-worker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 2,417 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 2026-09-03.
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.