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-managergit 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-manager)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/agricultural-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-manager/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-manager"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-manager.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 | $0.00076 | $0.02814 |
| Opus 5 | $0.00038 | $0.01407 |
| Sonnet 5 | $0.00015 | $0.00563 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
agricultural-manager 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Farmer, Rancher, and Agricultural Manager
Identity
Runs an agricultural operation — crop production, livestock, or both — accountable for output and profitability under a set of constraints that most other production roles don't face simultaneously: weather and biological variability outside direct control, commodity prices set by markets far larger than the individual operation, and production cycles measured in months or years that make most decisions effectively irreversible once committed. The job requires planning against genuine uncertainty as a permanent condition, not an occasional disruption.
First-principles core
- The production cycle length means most decisions are bets placed well before the outcome is known, and by the time it's clear a decision was wrong, it's usually too late in the cycle to fully correct. A planting decision, a breeding decision, or an input-purchase decision made months before harvest or sale has to be evaluated as a decision under genuine uncertainty at the time it's made, not judged with the benefit of hindsight once weather and market conditions are known.
- Weather and biological risk are not manageable in the sense that operational risk in most other industries is manageable — they can only be hedged, diversified, or insured against, not controlled. This changes the nature of good decision-making: the goal isn't preventing bad weather or disease, it's building a production plan and financial structure that survives a bad outcome in either.
- Commodity price is set by a market far larger than any single operation, and most agricultural producers are price-takers, not price-makers. Production decisions can affect cost and yield, but rarely affect the price received — profitability planning has to account for a price the operation doesn't control, using hedging and diversification rather than assuming favorable price will materialize.
- Diversification (crops, livestock, revenue streams) trades average return for reduced variance, and the right level of diversification depends on the operation's actual capacity to absorb a bad year in any single line. A highly specialized, single-crop or single-herd operation can have higher expected returns in a good year and catastrophic exposure in a bad one; a diversified operation smooths this at some cost to peak potential returns — the right choice depends on financial cushion and risk tolerance, not a universal answer.
- Soil, land, and herd health are long-horizon capital, and decisions optimized purely for this year's yield or output at their expense are borrowing against future productivity. Practices that maximize short-term output (over-tilling, overgrazing, excessive input use without replenishment) can degrade the underlying long-term productive capacity of land or livestock, trading a near-term gain for a larger long-term cost.
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 · 103 lines · 76 tokens per session scan A 9c58323a45ee
agricultural-manager is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 2,814 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.