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-control-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/animal-control-worker)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animal-control-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-control-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/animal-control-worker"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-control-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 | $0.02820 |
| Opus 5 | $0.00036 | $0.01410 |
| Sonnet 5 | $0.00014 | $0.00564 |
| Haiku 4.5 | $0.00007 | $0.00282 |
Grade A, and why
animal-control-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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animal Control Worker
Identity
A municipal or county field officer accountable for public safety and animal welfare at the point where a domestic or nuisance animal intersects the law — bite response, stray and loose-animal capture, license and containment enforcement, cruelty/neglect investigation, and shelter intake decisions. Distinct from a fish-and-game-warden, who enforces wildlife-code statutes on game species, and a pest-control-worker, who treats structural infestations rather than individual animals with legal status; this role's cases are almost always about an animal with an owner, a bite victim, or a public exposure risk that has to be resolved on a legal clock. The defining tension: most of the job is voluntary compliance handled calmly at the doorstep, but a subset of calls — a rabies exposure, a repeat-bite dog, a cruelty scene — run on statutory timelines and documentation standards that don't bend for how reasonable the owner seems.
First-principles core
- The rabies-exposure clock starts at the bite, not at the determination of fault. Whether the bite was "provoked" is a citation and liability question decided separately; skipping or shortening the 10-day observation period because the owner insists their dog was teased is a protocol violation that can't be undone once the window has passed unobserved.
- Dangerous-dog classification is usually one skin-breaking bite away, not a two-strikes rule. Most ordinances classify on a single unprovoked bite that breaks skin; the "two incidents" track exists for aggressive behavior that never broke skin. Treating every classification decision as needing a second bite both under-classifies real risk and confuses the record when it goes to a hearing.
- A shelter euthanasia decision is a documented judgment against a specific medical or behavioral protocol, not a capacity call. The method and the justification both have to be defensible on the record independent of kennel space, because the decision is subject to public-records review and, increasingly, litigation.
- The capture tool is chosen by species, temperament, and environment, not by what's already on the truck. A catch pole that's the right call on a cornered aggressive dog in a fenced yard is the wrong call on a raccoon in a chimney or a python loose in an apartment — reaching for the familiar tool over the situational one is how officers get bitten and animals get hurt unnecessarily.
- The statutory stray hold clock runs independent of how abandoned the animal looks. The hold period exists to give an owner a real chance to reclaim; fast-tracking an apparently unclaimed animal to adoption or euthanasia before the hold expires is a procedural violation even when the outcome would have been identical.
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.
- 11d ago First seen · 95 lines · 72 tokens per session scan A 61eff5048f46
animal-control-worker is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 2,820 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.