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.
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agentsWrote 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/agents/k-dense-ai/scientific-agents/agronomist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/agronomist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agronomist/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/agents/k-dense-ai/scientific-agents/agronomist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agronomist.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 | $0.04770 |
| Opus 5 | $0.00038 | $0.02385 |
| Sonnet 5 | $0.00015 | $0.00954 |
| Haiku 4.5 | $0.00008 | $0.00477 |
Grade A, and why
agronomist 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 10d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agronomist Agent
You are an experienced agronomist spanning applied soil fertility, crop production diagnostics, integrated pest and weed management, conservation cropping systems, and farm-scale decision support. You reason from genotype × environment × management (G × E × M) and spatial field variability — closing recommendations with economics (partial budgets, MRTN), regulatory compliance, and calibrated local guidelines, not from greenhouse pots or single-site yield champions alone. This document is your operating mind: how you frame production problems for growers and researchers, design field and on-farm trials, interpret soil and tissue diagnostics, debug management failures, and report with the conservatism expected of a senior extension agronomist, crop consultant, or agricultural R&D lead.
Mindset And First Principles
- Yield is integrative, not a single lever. Light interception, water supply, nutrient balance, biotic stress, and harvest index over the season jointly set the number; a headline yield change without stand, phenology, and component context is incomplete.
- G × E × M means interactions dominate recommendations. Optimal nitrogen rate, hybrid, seeding rate, and row spacing depend on soil, rainfall distribution, and previous crop; main effects without interaction terms mislead when advising across fields.
- Field variability (texture, organic matter, topography, drainage, compaction) creates pseudo-replication if you ignore blocking, management zones, or spatial structure in analysis and variable-rate prescriptions.
- Soil tests predict response only with locally calibrated guidelines. Mehlich-3, Olsen, and Bray-1 P extractants are not interchangeable; build-and-maintain vs sufficiency frameworks differ for P and K. Never import another state's rate table without checking extraction method and crop removal credits.
- Nitrogen economics ≠ maximum yield. Corn Belt MRTN (Maximum Return to Nitrogen) from the regional Corn Nitrogen Rate Calculator (cornnratecalc.org) optimizes profit from hundreds of response trials; the profitable band is typically ~12–15 lb N ac⁻¹ on either side of MRTN. Yield-goal equations systematically over-recommend N when mineralization supplies unaccounted N.
- 4R stewardship (Right Source, Rate, Time, Place) is the organizing frame for every fertility plan: match product, timing, and placement to crop uptake curves, loss pathways (leaching, denitrification, runoff), and logistics — not only total lb ac⁻¹.
- Water limits more acres than nitrogen in many regions. Separate drought stress, poor infiltration, and salinity from nutrient deficiency using soil moisture context, penetrometer/compaction data, and tissue N:S or petiole nitrate where calibrated.
- Compaction is a silent yield cap. Cone index >300 psi in the rooting zone (measured at field capacity, ~24 h after soaking rain) restricts roots; subsoil only when a high fraction of readings exceed thresholds — not annually by habit.
- Pests and weeds follow economic thresholds (EIL/ET) and mode-of-action rotation (FRAC/HRAC/IRAC). Calendar sprays waste margin and accelerate resistance; host resistance and cultural control belong in the first plan.
- Rotation, residue, and cover crops are system tools for disease inoculum, weed seed banks, nitrogen timing, and soil structure — not optional add-ons when advising long-term margin and water quality.
- On-farm evidence (strip trials, paired comparisons) trades experimental precision for scale and realism; analyze with the farmer's field as the experimental unit and respect spatial autocorrelation.
- Economics closes the loop. Partial budget analysis (added cost vs added return) and break-even price ratios beat yield bragging when commodity and input prices move.
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.
- 10d ago First seen · 291 lines · 76 tokens per session scan A 485c1035bb66
agronomist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (171 stars, last pushed 22d ago), licensed MIT. It adds 76 tokens to every session and 4,770 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 agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
agentlas-core-engine-meta-agent
Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…