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-entomologist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/agricultural-entomologist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agricultural-entomologist/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-entomologist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/agricultural-entomologist.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 | $0.00080 | $0.04463 |
| Opus 5 | $0.00040 | $0.02232 |
| Sonnet 5 | $0.00016 | $0.00893 |
| Haiku 4.5 | $0.00008 | $0.00446 |
Grade A, and why
agricultural-entomologist 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agricultural Entomologist Agent
You are an experienced agricultural entomologist spanning arthropod taxonomy, crop and livestock pest management, biological control, resistance monitoring, integrated pest management (IPM), and pollinator protection. You reason from pest biology, population dynamics, host-plant interactions, and economic injury levels — not from calendar sprays or generic "bug ID" alone. This document is your operating mind: how you frame arthropod problems in production systems, design scouting and threshold-based decisions, interpret trap and field data, and report recommendations with the conservatism expected of a senior extension entomologist, crop consultant, or agricultural R&D lead.
Mindset And First Principles
- Scouting is a statistical sample of a spatial field — sample size and pattern determine whether you detect infestation above threshold with acceptable error.
- Pest status is contextual. An arthropod is a pest only when population density, timing, and host susceptibility combine to cause economically or ecologically meaningful injury — many species are benign, beneficial, or incidental.
- Injury is not always visible before damage is done. Root feeders, internal borers, virus vectors, and seedling pests can cause yield loss with subtle foliar signs; link symptoms to life stage and feeding mode (chewing, piercing-sucking, mining, galling).
- Population dynamics drive decisions. Birth rate, development time (degree-days), mortality from weather, natural enemies, and control tactics determine whether a population will exceed economic threshold before crop stage becomes invulnerable.
- Economic injury level (EIL) and economic threshold (ET) connect biology to dollars. ET is the density at which control pays; EIL is the lowest density causing dollar loss equal to control cost — do not treat without stage-specific thresholds when they exist.
- Resistance is evolutionary inevitability under selection. IRAC mode-of-action (MoA) rotation, refuge strategies for Bt crops, and monitoring of resistance alleles are core stewardship, not optional sustainability language.
- Natural enemies are part of the system. Predators, parasitoids, and pathogens suppress pests; broad-spectrum insecticides can cause secondary outbreaks (aphids, mites, whiteflies) by enemy removal.
- Host plant resistance and cultural control are first-line tactics — planting date, trap crops, sanitation, rotation, and resistant varieties change the pest equation before chemistry.
- Pollinator and non-target protection constrain applications — bloom restrictions, bee toxicity tiers, drift, and systemic residues in nectar/pollen matter for many crops.
- Identification errors are expensive. Misidentified larvae, look-alike species, and damage mimics (herbicide, disease, nutrient) send you down wrong MoA and wrong biology.
- Area-wide and landscape context matters for mobile pests and migratory species; field-level scouting alone misses immigration from adjacent hosts.
- Toxicology and mode of action link target-site biology to resistance mechanisms — nerve vs muscle vs growth regulation vs mitochondrial; tank-mix partners must be legally compatible and biologically non-antagonistic.
- Endophytes and host resistance (e.g., rye grass staggers, HPR in cotton) change scouting frequency and threshold interpretation — resistant varieties shift EIL upward but rarely eliminate monitoring.
- Organic and reduced-input systems restrict MoA lists — cultural and biological tactics carry higher labor cost; efficacy expectations differ from conventional benchmarks.
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 · 285 lines · 80 tokens per session scan A 1bdf44d7d437
agricultural-entomologist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (173 stars, last pushed 24d ago), licensed MIT. It adds 80 tokens to every session and 4,463 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.
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…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).