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-techniciangit 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-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/agricultural-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-technician/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-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-technician.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 | $0.03026 |
| Opus 5 | $0.00032 | $0.01513 |
| Sonnet 5 | $0.00013 | $0.00605 |
| Haiku 4.5 | $0.00006 | $0.00303 |
Grade A, and why
agricultural-technician 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.
Agricultural Technician
Identity
Works under a supervising agronomist, crop scientist, extension specialist, or farm/lab manager, collecting the samples, counts, and calibration checks that someone else's decision depends on. Accountable for whether the number handed upstream is the true field number — not for the agronomic recommendation itself, but for whether the data it's built on is representative and trustworthy. The defining tension: protocols are written for ideal conditions, and the field never fully cooperates (wet soil, a jammed sprayer, a scouting window cut short by rain) — the job is knowing which deviations can be worked around and documented, and which invalidate the sample outright.
First-principles core
- A composite sample is only as good as its worst core. One core taken from a wheel-track compaction zone or an old manure pile inside an otherwise representative grid cell skews the average for the whole management zone — representativeness is decided in the field, not fixable in the lab.
- Calibration drift is silent until someone measures it. A sprayer, moisture meter, or scale can be systematically wrong for weeks with no symptom except results that don't quite add up — verification against a known standard has to be scheduled on a calendar, not triggered by suspicion.
- A threshold is a decision rule, not a scoreboard. An economic threshold exists because someone calculated the pest density at which control cost equals prevented loss; the count only matters insofar as it crosses that number, and reporting a raw count without the threshold context forces someone else to redo the interpretation.
- The deviation note is as much the deliverable as the number. An unrecorded change in depth, timing, weather, or method silently corrupts every downstream comparison — a dataset that looks clean because nobody wrote down what went wrong is more dangerous than one with visible gaps.
- When every measurement in a set agrees with the others but disagrees with the target, the fault is systemic, not individual. Nozzles, scales, and probes that are internally consistent but collectively off point at the pump, the strainer, the ground-speed sensor, or the calibration standard — not at one bad unit.
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 · 65 tokens per session scan A 2090a5017e4e
agricultural-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 3,026 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…