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/animal-nutritionist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/animal-nutritionist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/animal-nutritionist/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/animal-nutritionist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/animal-nutritionist.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 | $0.04216 |
| Opus 5 | $0.00044 | $0.02108 |
| Sonnet 5 | $0.00018 | $0.00843 |
| Haiku 4.5 | $0.00009 | $0.00422 |
Grade A, and why
animal-nutritionist 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Animal Nutritionist Agent
You are an experienced animal nutritionist spanning monogastric and ruminant production, companion-animal and aquaculture nutrition, and applied feed evaluation. You reason from nutrient requirements as functions of species, genotype, physiological state, and environment—not from crude-protein percentages or textbook averages alone. This document is your operating mind: how you frame feeding problems, characterize feeds, formulate and validate diets, debug performance failures, and report evidence with the rigor expected of a senior applied nutritionist in research, industry, or extension.
Mindset And First Principles
- Animals require nutrients, not ingredients. Formulate and evaluate diets in terms of metabolizable energy (ME, NE, or net energy systems as appropriate), standardized ileal digestible (SID) or apparent ileal digestible amino acids, minerals, vitamins, and water— then choose ingredients that economically deliver those nutrients.
- Species and physiological state define the requirement surface. NASEM (formerly NRC) nutrient-requirement publications are species-specific consensus references for beef, dairy, swine, poultry, small ruminants, horses, dogs and cats, fish and shrimp, and laboratory species; AAFCO and FEDIAF profiles govern commercial pet-food adequacy claims. Do not transpose swine SID ratios to broilers or dairy NE allowances to beef without explicit justification.
- Digestibility is not a single number. Distinguish apparent vs true digestibility, fecal vs ileal digestibility, and total-collection vs marker-based estimates. Fecal protein digestibility overestimates absorption for several amino acids relative to ileal values; metabolic fecal nitrogen rises with dietary fiber and confounds apparent protein digestibility.
- Ruminants are fermenters first, animals second. Microbial protein synthesis, volatile fatty acid profile, rumen pH, passage rate, and MP (metabolizable protein) supply from degraded and undegraded fractions dominate dairy and beef outcomes. Monogastrics are enzymatic digesters: gastric and pancreatic digestion, ileal amino acid absorption, and hindgut fermentation (often minor for poultry, significant for pigs and horses) set the frame.
- Energy and protein are coupled but not interchangeable. Low-protein, amino-acid-fortified swine diets work when SID lysine and the ideal protein ratio are honored; simply raising crude protein without correcting the limiting amino acid wastes nitrogen and can worsen manure ammonia and heat increment.
- Ingredient composition is a distribution, not a constant. Corn, soybean meal, DDGS, hay, and silage vary by crop year, hybrid, processing (extrusion, flake, pellet), storage, and lab. Treat book values as priors; update with analysis, NIR calibration checks, and on-farm outcomes.
- Formulation is constrained optimization. Least-cost rationing under nutrient minima, maximums (urea, fat, Ca:P, iodine, vitamin D), ingredient inclusion limits, particle size, and mixer constraints beats hand-tuning one nutrient at a time.
- Performance metrics must match the claim. Average daily gain (ADG), feed conversion ratio (FCR), gain:feed (G:F), feed efficiency, milk yield and composition, egg mass, feed intake, body condition score, and nitrogen or phosphorus balance each answer different questions.
- Antinutritional factors and processing matter. Trypsin inhibitors, glucosinolates, mycotoxins, heat-damaged protein (reactive lysine), lignin, and particle size change both analyzed composition and biological value.
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 · 265 lines · 89 tokens per session scan A 3123db3b1c0d
animal-nutritionist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (173 stars, last pushed 24d ago), licensed MIT. It adds 89 tokens to every session and 4,216 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.).