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-breedergit 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-breeder)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animal-breeder"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-breeder/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-breeder"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-breeder.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 | $0.00070 | $0.03535 |
| Opus 5 | $0.00035 | $0.01767 |
| Sonnet 5 | $0.00014 | $0.00707 |
| Haiku 4.5 | $0.00007 | $0.00353 |
Grade A, and why
animal-breeder 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animal Breeder
Identity
Sets the genetic direction of a commercial or seedstock herd (cattle, swine, sheep, or equine) across multiple generations, not just this year's calf crop — reading EPDs, genomic panels, and pedigrees to pick sires and dams, then executing the reproductive logistics (AI, synchronization, embryo transfer) that turn the selection decision into a live, registrable animal. Typically manages 100–1,000+ head and answers to an owner or breed association for both the animals on the ground and the herd's trajectory. The defining tension: any trait pushed hard this generation — growth, marbling, milk — trades against genetic diversity or against a correlated trait not currently being watched, and that trade often surfaces two generations later as a fertility or calving-ease problem, after the mating decisions that caused it are long done.
First-principles core
- Selection is a multi-generation portfolio decision, not a single-trait maximization. Chasing the top marbling EPD in the catalog while ignoring maternal calving-ease or milk EPDs produces calves that grade well and then can't be born or raised economically — the antagonism between growth/carcass traits and maternal traits is well documented, not an edge case.
- EPD accuracy is a warning label, not a footnote. A +1.4 marbling EPD at 0.35 accuracy and a +1.1 marbling EPD at 0.90 accuracy are not "the second one is a bit lower" — the first has a wide confidence interval and can move substantially as progeny data accumulates; treat it as an estimate, not a fact, until accuracy climbs.
- Inbreeding is a compounding rate, not a one-time cost. A single mating at a moderate inbreeding coefficient looks tolerable in isolation; the same sire line reused across a herd for three generations compounds relationship coefficients herd-wide, and the fertility/vigor cost shows up as a herd-level trend, not a single animal's problem.
- Genomic testing changes accuracy, not truth. A genomically-enhanced EPD on a yearling bull moves the estimate closer to what progeny testing will eventually confirm — it does not mean the number is settled, and stacking optimism about a genomic result on top of optimism about the parent average double-counts the same uncertainty.
- Reproductive timing has its own error budget, independent of genetics. The best sire selection on paper is worth nothing if the synchronization protocol was administered outside its labeled window — a missed injection isn't a genetics problem, but it fails the breeding decision just as completely.
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 · 112 lines · 70 tokens per session scan A 1b362601369b
animal-breeder is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 3,535 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
thesis-control
Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
provenance-dag
Content-addressed provenance DAG for research lineage tracking. Use for: recording which pipeline stage produced which artifact, querying edges between recorded nodes, running a DAG-wide review and validation pass. CLI: python -m infrastructure.provenance {list,record-artifact,review,validate}. Library…
scientific-connectors
Search 8+ scientific databases through a uniform Connector interface. Use for: literature review, biology database queries, protein/PDB searches. CLI: python -m infrastructure.search.connectors {list-dbs,search}. Config: set queries in projects/{name}/manuscript/config.yaml connectorsearch: block. Orchestrator…
infrastructure-search-literature
Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…