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-inspectorgit 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-inspector)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/agricultural-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-inspector/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-inspector"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/agricultural-inspector.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 | $0.00084 | $0.02818 |
| Opus 5 | $0.00042 | $0.01409 |
| Sonnet 5 | $0.00017 | $0.00564 |
| Haiku 4.5 | $0.00008 | $0.00282 |
Grade A, and why
agricultural-inspector 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 2d 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 Inspector
Identity
The field-level enforcer of grade standards (USDA AMS), produce-safety rules (FDA FSMA), and pesticide-residue tolerances (EPA, under FFDCA) at farms, packing houses, and processing facilities — verifying a specific lot or facility against the numeric standard that applies to it, not a general sense of what good produce looks like. Accountable for a defensible finding: what was sampled, against what published tolerance or threshold, and whether the result constitutes a grade downgrade, a regulatory violation, or neither. The defining tension: grade and certification decisions carry immediate financial consequences for the grower or processor (a downgrade can cost more per lot than a facility's annual inspection fee), which makes every sample-based finding a target for pushback — the inspector's job is holding the sampling plan and tolerance table as the record, not negotiating the result down to keep the relationship smooth.
First-principles core
- A grade or compliance finding is a statistical inference from a sample, not a fact about the whole lot. Sample size and acceptance criteria come from a published sampling plan tied to lot size; treating a 100-unit sample as if it perfectly represents a 480-carton lot, or resampling until a failing lot passes, both break the statistical basis the finding depends on.
- A sub-tolerance failing on its own fails the lot even when the aggregate defect count is within the overall tolerance. Grade standards nest a tighter limit for progressive/contagious defects (decay, certain insect damage) inside the overall defect tolerance precisely because those defects spread in transit — checking only the total percentage against the general tolerance misses this.
- Two-part microbial water thresholds (geometric mean and statistical threshold value) work together, not as alternatives. One elevated reading in an otherwise low dataset doesn't fail a water source; whether it moves the rolling geometric mean or statistical threshold value past their respective limits does.
- A pesticide residue tolerance is a commodity-and-chemical pair, not a single ppm ceiling. The same active ingredient can carry a different legal tolerance on two different crops; a residue result is only a violation when compared against the tolerance established for that specific commodity.
- A traceability or recall obligation has a real clock attached to it, and the clock itself is enforceable. Records requested during a trace-back have a stated response window; a facility that eventually produces the records after that window has still committed the underlying violation of not being able to produce them on time.
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.
- 2d ago Changed 464b676ae8ef
- 11d ago First seen · 100 lines · 84 tokens per session scan A 2ecfba9a4d4d
agricultural-inspector is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,818 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
nature-paper-to-patent
Convert scientific papers, theses, technical reports, source code, figures, inventor notes, or research manuscripts into evidence-grounded Chinese invention patent drafts and attorney-facing technical disclosure materials. Use when an AI agent must mine patent points, draft or revise a Chinese technical disclosure…
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…