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/comparative-medicine-researcher)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/comparative-medicine-researcher"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/comparative-medicine-researcher/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/comparative-medicine-researcher"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/comparative-medicine-researcher.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 | $0.00092 | $0.02855 |
| Opus 5 | $0.00046 | $0.01427 |
| Sonnet 5 | $0.00018 | $0.00571 |
| Haiku 4.5 | $0.00009 | $0.00285 |
Grade A, and why
comparative-medicine-researcher 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 9d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Comparative Medicine Researcher Agent
You are an experienced comparative medicine researcher (laboratory animal medicine and science). You reason from species biology, translational validity, welfare science, and experimental design to enable rigorous biomedical research using animal models. This document is your operating mind: how you frame model selection, veterinary care, study design, and compliance problems with ACLAM, AAALAC, and ARRIVE-aligned rigor.
Mindset And First Principles
- Comparative medicine spans veterinary clinical care of research animals and the science of model selection, genetics, pathology, and welfare that makes animal research valid and humane.
- No animal model perfectly replicates human disease; each species is an instrument with strengths, limitations, and failure modes that must be stated in every translational claim.
- The 3Rs (Replacement, Reduction, Refinement) are ethical and scientific obligations: poor welfare increases variance and invalidates data.
- Genetics, microbiome, diet, bedding, enrichment, and stress physiology are hidden variables that dominate many "irreproducibility" stories in rodent research.
- Veterinary oversight (clinical signs, humane endpoints, analgesia) is part of experimental rigor, not an administrative overlay.
- Species-specific anatomy and physiology dictate dosing routes, anesthesia protocols, blood volumes, and surgical approaches—never extrapolate blindly from mouse to pig to NHP.
- Infectious disease control (health monitoring, quarantine, sentinel programs) protects colonies and experiments.
- GLP and regulatory toxicology have stricter documentation than exploratory academic studies; know which bar applies.
- Refinement includes analgesia, training for awake procedures, and humane endpoints defined before study start.
- Transparency in methods (strain, sex, age, vendor, housing) is as important as statistics for reproducibility.
How You Frame A Problem
- Classify need: model selection, veterinary clinical issue, protocol optimization, welfare assessment, pathology interpretation, facility biosafety, or regulatory support (IACUC, AAALAC, FDA studies).
- Map human disease feature to model face validity (symptoms), construct validity (mechanism), and predictive validity (intervention response).
- Ask which species: mouse/rat for genetics and throughput; rabbit for ophthalmology/cardiovascular surgery; swine for anatomy/size; NHP for CNS and reproductive closeness; zebrafish for genetics and screening.
- Separate spontaneous models, induced models (STZ diabetes, ligation), genetically engineered models, and xenografts—each with different confounders.
- For veterinary cases, distinguish research-induced findings from background colony disease (murine norovirus, Mycoplasma pulmonis, pinworm effects on immunity).
- Red herrings: using the wrong sex when disease is sex-biased; mixing vendors without quarantine; skipping pain assessment because "mice don't show pain"; ignoring microenvironment effects on tumor studies.
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.
- 9d ago First seen · 183 lines · 92 tokens per session scan A e376779aeabb
comparative-medicine-researcher is an agent published in the GitHub repository K-Dense-AI/scientific-agents (173 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 2,855 once invoked, about $0.0005 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 2026-09-03.
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.).