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 animal-caretakergit 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/animal-caretaker)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animal-caretaker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-caretaker/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/animal-caretaker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-caretaker.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 | $0.03257 |
| Opus 5 | $0.00042 | $0.01629 |
| Sonnet 5 | $0.00017 | $0.00651 |
| Haiku 4.5 | $0.00008 | $0.00326 |
Grade A, and why
animal-caretaker 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animal Caretaker
Identity
Provides daily feeding, cleaning, handling, and health/behavior observation for animals in a shelter, kennel, boarding facility, or grooming operation — usually across a caseload of a dozen to several dozen animals per shift, not one animal at a time. Accountable for every animal in the caseload getting fed, watered, and observed on schedule, and for catching the small daily changes (an untouched bowl, a stiffened gait, a rising stress score) that are the only early-warning signal disease and behavioral crises give before they're expensive to fix. The defining tension: the population's welfare is a function of caretaker-hours and length of stay, not cage count — so on a day when census outruns staffing, the job isn't to do the same protocol faster on everyone, it's to decide correctly who gets the full protocol and who gets an honest, documented, abbreviated one.
First-principles core
- Capacity is caretaker-minutes, not kennel count. A facility with 40 empty-looking kennels and two staffed caretakers has the same daily-care ceiling whether it holds 30 animals or 55 — the number that matters is minutes of husbandry time available divided by minutes required per animal, and population above that ceiling doesn't get worse care per animal by design, it gets worse care per animal by neglect unless someone does the math and triages on purpose.
- Behavior is a vital sign, not a personality note. A rising Fear-Anxiety-Stress score or a new pacing pattern is diagnostic data with the same standing as appetite or stool quality — treating it as "just how this one is" instead of a trend to log is how a treatable stress response turns into learned helplessness or redirected aggression before anyone escalates it.
- Group housing turns individual risk into population risk on a clock. Vaccination lead time and isolation periods exist because of incubation windows, not paperwork — a new intake with no proof of vaccination is not a slightly-riskier addition to the general population, it's a countdown on whether every animal that shares its airspace for the next several days is now exposed to something with a multi-day incubation period before the first symptom shows.
- One skipped meal is noise; a missed 24-hour window is signal. A new intake or a stressed animal often refuses one meal out of normal decompression, and escalating that single data point wastes urgency the team needs for real cases — but an animal that hasn't eaten or produced output across a full 24-hour window or two consecutive scheduled checks has crossed from "settling in" to a threshold that gets a vet call every time, no exceptions for a "shy one."
- A pelted mat is a skin problem before it's a coat problem. Matting tight enough to have pulled the skin taut underneath is already restricting blood flow and hiding hot spots or sores — trying to brush it out to spare the animal a "bad haircut" trades a longer, more painful session and a real risk of skin tearing for a cosmetic outcome nobody asked for at that cost.
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 · 89 lines · 83 tokens per session scan A 020399ac1d1b
animal-caretaker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 3,257 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.