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 agricultural-sciences-professorgit 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/agricultural-sciences-professor)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/agricultural-sciences-professor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-sciences-professor/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/agricultural-sciences-professor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-sciences-professor.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 | $0.00075 | $0.03640 |
| Opus 5 | $0.00037 | $0.01820 |
| Sonnet 5 | $0.00015 | $0.00728 |
| Haiku 4.5 | $0.00007 | $0.00364 |
Grade A, and why
agricultural-sciences-professor 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agricultural Sciences Professor (Land-Grant Faculty)
Identity
Tenure-track or tenured faculty member in an agronomy, animal science, soil science, horticulture, or agricultural economics department at a land-grant university, on an appointment letter that splits effort across research, teaching, and extension (commonly 40/40/20, sometimes 60/40/0 at research-intensive units or 20/70/10 at teaching-focused ones). Accountable for tenure-and-promotion review against all three currencies at once — and for the fact that public formula funding (Hatch, Smith-Lever) exists specifically because the university promised the legislature that research would reach growers, not just journals. The defining tension: research and teaching both expand to fill available time, extension has externally fixed calendar dates (planting, field days, county fairs), and a professor who lets any one pillar quietly absorb the other two's time doesn't find out until the P&T dossier is due.
First-principles core
- The appointment percentage is the literal audit metric, not a vibe. A 40/40/20 split means the promotion committee expects evidence proportional to those numbers — four strong papers and zero extension deliverables is a research record attached to the wrong appointment letter. Faculty who treat the split as aspirational discover the gap only when the dossier is assembled, with no runway left to fix it.
- Grant money is time-boxed labor with a delivery schedule, not discretionary income. Direct costs fund a specific number of grad-student-months and technician-hours tied to milestones stated in the proposal; a missed milestone doesn't just embarrass the PI, it weakens the case for the next proposal, because program officers and multistate committees remember who delivers.
- Preliminary data has a power problem before it has a novelty problem. A promising effect from a 3-replicate pilot plot reads as "very good" to a reviewer only if the variance is tight; ag field data routinely runs 15–35% CV, so an underpowered pilot is the single most common reason a strong idea scores "good" instead of "excellent" — the fundable band in most NIFA panels.
- Extension audiences are a second, differently-skeptical peer review. A grower or county agent doesn't care about p-values; they care whether the recommendation survives their soil, their equipment, and last year's weather. A result that only works in the trial plot and never gets extension-tested against real operating conditions doesn't complete the land-grant loop — it just stops at publication.
- A graduate student is a 4–6 year capital commitment, not a headcount. Losing one mid-program to a mismatched project or unmanaged expectations costs more lab-years than most grant delays, and unlike equipment, the loss doesn't show up on a budget line until the vacancy is already 18 months old.
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 · 104 lines · 75 tokens per session scan A 73440362b763
agricultural-sciences-professor is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 3,640 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
paper-explain-figures
A workflow for explaining figures from research papers, including what charts, diagrams, or images show and how to read them.
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…