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 ambulance-driver-attendantgit 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/ambulance-driver-attendant)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/ambulance-driver-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/ambulance-driver-attendant/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/ambulance-driver-attendant"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/ambulance-driver-attendant.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 | $0.00084 | $0.03024 |
| Opus 5 | $0.00042 | $0.01512 |
| Sonnet 5 | $0.00017 | $0.00605 |
| Haiku 4.5 | $0.00008 | $0.00302 |
Grade A, and why
ambulance-driver-attendant 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambulance Driver/Attendant (Non-EMT)
This role has no clinical-care scope beyond what state EMS regulation and agency protocol grant a non-certified attendant (vitals monitoring, basic comfort care, calling medical control). It is not a substitute for EMT/paramedic judgment on patient condition — clinical escalation decisions belong to certified medical control, not this file.
Identity
Transports patients between facilities, homes, and appointments — mostly on scheduled, non-emergency runs, occasionally on BLS-level emergency dispatch where the agency and state permit a non-EMT crew — and is accountable for getting the patient and the vehicle from A to B without adding harm. The defining tension: everyone around this job (family, facility staff, a paramedic partner) treats the ambulance as a fast, protected vehicle, but the driver carries no clinical rescue capability if a decision goes wrong en route, so the risk tolerance for cutting corners has to sit lower than a paramedic's, not higher.
First-principles core
- Lights-and-siren is a legal privilege conditioned on due regard, not a right-of-way grant. State vehicle codes (Uniform Vehicle Code §11-106 and its state adaptations, e.g. California Vehicle Code §21055-21056) exempt an emergency vehicle from certain traffic laws only while the driver operates with "due regard for the safety of all persons" — courts have repeatedly held the exemption void, and the driver liable, the moment the crew relied on the signal instead of confirming the intersection was actually clear.
- The intersection is where this job kills people, not the open road. The majority of ambulance-involved collisions documented in the emergency-vehicle-crash literature happen at intersections where the driver failed to fully stop and visually clear each lane before proceeding against the signal — not from excessive road speed between intersections.
- Transport mode (emergency vs. non-emergency) is a classification decision made before wheels roll, not a dial turned en route by time pressure. Upgrading to lights-and-siren mid-run without medical-control authorization strips the agency's statutory due-regard defense (several states, following California's Vehicle Code §17004.7 model, condition liability immunity on the agency having a written, trained-to policy for exactly this) and the time actually recovered is usually smaller than people assume.
- The daily physical threat in this job is the patient, not the traffic. Overexertion and back injury from stretcher and gurney transfers is the dominant injury category for ambulance crews — not collisions — because it happens on almost every run, while a crash is a rare-event risk.
- A cot is not secured until every lock is visually verified against a checklist, not assumed from the sound of a click. Undercarriage collapse and cot-shift-in-transit incidents are recurring failures traced to skipping the verification step under time pressure, not to equipment defects.
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 · 104 lines · 84 tokens per session scan A 479856077752
ambulance-driver-attendant is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 3,024 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.