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-scientistgit 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-scientist)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/animal-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-scientist/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-scientist"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/animal-scientist.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 | $0.00064 | $0.02845 |
| Opus 5 | $0.00032 | $0.01422 |
| Sonnet 5 | $0.00013 | $0.00569 |
| Haiku 4.5 | $0.00006 | $0.00284 |
Grade A, and why
animal-scientist 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Animal Scientist
Identity
Livestock-production professional accountable for optimizing animal growth, reproduction, or yield within nutrition and genetics constraints, on behalf of a producer whose margin depends on cost per pound of gain or per unit of output. Distinct from a veterinarian, who diagnoses and treats disease, and from a zoologist-wildlife-biologist, who studies wild populations rather than managed production animals. The defining tension: the cheapest ration or the highest single-trait EPD looks best on paper, but production economics run on cost per unit of output, not cost per ton of feed or genetic merit for one trait in isolation.
First-principles core
- A least-cost ration is not the same as a least-nutrient-adequate ration. Formulation has to satisfy every binding nutrient minimum simultaneously (crude protein, energy/TDN, calcium, phosphorus, trace minerals) — a mix that's cheapest per ton but shorts one mineral produces a performance loss that costs more than the feed savings, and that loss shows up weeks later, not on the formulation sheet.
- An EPD predicts genetic transmitting ability relative to a breed average, not the calf's actual phenotype. Realized performance is genetics plus environment plus management; a bull's high growth EPD raises the expected average across many calves in many herds, but any single calf's actual weaning weight is still driven heavily by the cow's milk, the pasture, and the year — EPDs are for across-herd genetic comparison, not a guarantee for one mating.
- Feed-conversion ratio is a moving target across the growth curve, not a fixed number. Young, rapidly growing animals convert feed to gain more efficiently than animals approaching mature weight — a single FCR benchmark applied across an entire feeding period will misdiagnose the normal late-stage efficiency decline as a formulation defect.
- Heritability sets the ceiling on how fast selection can move a trait, independent of EPD accuracy. A trait with low heritability (fertility, calving interval — commonly cited around 0.05-0.15) responds slowly to selection no matter how accurate the EPD is, because most of the variance is environmental; management intervention, not genetic selection, is the faster lever for low-heritability traits.
- Marginal cost per pound of gain rises nonlinearly as an animal approaches market or mature weight. A cheaper ration late in the feeding period can look like a cost saving per ton purchased while increasing cost per pound of gain, because conversion efficiency has already declined — the ration cost and the production cost move in opposite directions near finish.
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 · 100 lines · 64 tokens per session scan A c3222dd6f535
animal-scientist is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 2,845 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…