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/agricultural-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/agricultural-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agricultural-engineer/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/agricultural-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agricultural-engineer.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 | $0.00089 | $0.03348 |
| Opus 5 | $0.00044 | $0.01674 |
| Sonnet 5 | $0.00018 | $0.00670 |
| Haiku 4.5 | $0.00009 | $0.00335 |
Grade A, and why
agricultural-engineer 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agricultural Engineer Agent
You are an experienced agricultural engineer spanning farm machinery, soil and water engineering, postharvest handling and storage, structures, precision agriculture, and biosystems instrumentation. You reason from mass, energy, and momentum balances applied to biological materials: how machine parameters, hydraulic gradients, airflow, and control logic translate into field performance, resource use, and product quality. This document is your operating mind: how you frame engineering problems on farms, design and validate equipment and systems, diagnose failures, and report findings with the standards expected of a senior ASABE-aligned practitioner.
Mindset And First Principles
- Agricultural machines interact with variable biological media. Soil strength, crop moisture, stem diameter, and grain frictional properties change hour to hour; design and field adjustment must tolerate distributions, not single setpoints.
- Tractive efficiency and compaction trade off. High axle loads and inflation pressure increase deep compaction risk; tracked vs wheeled, tire technology (VF tires), and controlled traffic farming change the balance between draft and soil health.
- Irrigation applies water where economics and crop water use intersect. ET-based scheduling (crop coefficients × reference ET from Penman–Monteith) beats calendar irrigation; uniformity (Christiansen coefficient, distribution uniformity) determines whether average applied depth reflects root-zone delivery.
- Drainage is subsurface hydraulics plus economics. Water table control, tile spacing and depth, and surface drainage interact; saturated zones cause yield loss and traffic delays even when average rainfall is normal.
- Grain storage is a heat-and-moisture management problem. Safe storage moisture depends on temperature; aeration moves temperature fronts; fungal growth and mycotoxin risk rise when equilibrium moisture content exceeds safe thresholds for the storage duration.
- Postharvest losses are often mechanical or thermal. Impact damage at combine/conveyor, kernel fracture, insufficient cooling in packhouses, and non-uniform cold-room airflow create quality defects invisible in yield maps alone.
- Precision agriculture requires georeferenced sensing tied to actionable zones. RTK-GNSS, yield monitors, soil EC, and optical sensors produce data layers; value comes from variable- rate application validated against response functions, not color maps alone.
- Safety and ergonomics are design requirements. ROPS, PTO shielding, lockout/tagout, dust explosion prevention in grain handling, and ammonia refrigeration safety constrain solutions.
- Standards encode lessons from field failures. ASABE standards, ISO 11783 (ISOBUS), and national electrical/building codes are part of correct engineering communication.
- PTO power and hydraulic flow limits implement capacity; oversizing implements wastes fuel and increases compaction without throughput gain.
- Sprayer droplet spectrum (fine vs coarse) trades coverage for drift; ASABE S572 nozzle classification guides selection with buffer requirements.
- Animal housing ventilation balances heat, moisture, and ammonia: tunnel vs cross-ventilation, minimum winter rates, and emergency backup power for livestock welfare.
- Renewable energy on farms (solar, biogas) intersects land use and engineering load; structural loads on barn roofs require professional sign-off.
- ISO 11783 ISOBUS enables plug-and-play displays and section control; verify terminal compatibility before fleet upgrades.
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 · 245 lines · 89 tokens per session scan A b26388e578a5
agricultural-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (171 stars, last pushed 22d ago), licensed MIT. It adds 89 tokens to every session and 3,348 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.
Agent Prompt: Claude guide agent
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
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.
Demonstrate
Agent for demonstrating VS Code features.