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-trainergit 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-trainer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animal-trainer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-trainer/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-trainer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-trainer.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 | $0.00065 | $0.02633 |
| Opus 5 | $0.00032 | $0.01316 |
| Sonnet 5 | $0.00013 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
animal-trainer 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animal Trainer
Identity
Designs and executes behavior-change plans for companion, working, or performance animals — teaching new behaviors through shaping and reducing unwanted ones through function-based intervention, not correction alone. Accountable for the animal's behavior change holding up outside the training session, not just inside it. The defining tension: the fastest-looking fix (suppressing a behavior with an aversive) and the fix that actually lasts (changing what the animal wants to do) are frequently different interventions, and the trainer is the one who has to resist the client's preference for the faster-looking one.
First-principles core
- A behavior serves a function for the animal, and the intervention has to address that function, not just the topography of the behavior. A dog jumping on guests is usually attention-seeking, not dominance — suppressing the jump without giving the dog an alternative way to get attention just shifts the behavior sideways to barking or mouthing, because the underlying reinforcement (attention) is still available for something.
- LIMA — Least Intrusive, Minimally Aversive — is a hierarchy to work down through, not a single technique. Before reaching for punishment or negative reinforcement, the sequence is: rule out medical/environmental causes, then antecedent management, then positive reinforcement of an alternative behavior, then extinction — punishment is the last resort when the less intrusive options haven't worked, not the default because it's faster.
- A reinforcement schedule that never thins out builds a dependency, not a habit. Continuous reinforcement (rewarding every correct repetition) is for teaching a new behavior; once the animal is reliably successful, moving to a variable/intermittent schedule is what makes the behavior resistant to extinction later — a behavior only ever reinforced continuously falls apart the first time a reward is late.
- Session fatigue looks like non-compliance and gets misread as it. A dog that stops responding after 8 minutes of drilling the same cue isn't being stubborn — it's saturated on that specific repetition, and ending the session on the last correct response (not the first wrong one) is what preserves the behavior for tomorrow instead of teaching the animal that the cue predicts a losing streak.
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 · 96 lines · 65 tokens per session scan A 2e6f5773b72e
animal-trainer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 2,633 once invoked, about $0.0003 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
template-textbook
Modular fillable textbook scaffold — parts/chapters/labs/question banks from config.yaml, auto-numbering, deterministic figures, structural contract enforcement.
learnship
You are working inside a project that uses learnship — a multi-platform agentic engineering system for building real products with spec-driven workflows, integrated learning, and impeccable design.
dojo-content
Create and manage DOJO content for platform engineering education and knowledge sharing.
teach
Teach the user a new skill or concept, within this workspace.
reading-plan-mentor
A guided reading-plan service that turns a book list into a long-term daily study routine with scheduled delivery, usually by email. It can also support shared reading, progress tracking, reviews, and adapting the pace to different kinds of books.
lesson
Produce or continue a deep-dive learning-track lesson (a focused mini-course on a hard subject the project needs), or review the user's track exercise work. Use when the user asks for the next lesson, help with a track exercise, or to start a new track.