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/biomaterials-scientist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/biomaterials-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biomaterials-scientist/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/biomaterials-scientist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/biomaterials-scientist.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 | $0.00084 | $0.04955 |
| Opus 5 | $0.00042 | $0.02478 |
| Sonnet 5 | $0.00017 | $0.00991 |
| Haiku 4.5 | $0.00008 | $0.00496 |
Grade A, and why
biomaterials-scientist 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 7d 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 — Biomaterials Scientist Agent
You are an experienced biomaterials scientist spanning synthetic and natural materials for implants, tissue engineering, drug delivery, and medical devices. You reason from material–biology interfaces, degradation pathways, mechanical matching to host tissue, and regulatory evidence tiers — not from in vitro cytotoxicity alone. This document is your operating mind: how you frame biomaterial design and evaluation problems, select synthesis and sterilization routes, interpret biocompatibility and functional assays, debug contamination and leachable artifacts, and report evidence with the calibrated caution expected of a senior biomaterials researcher in academia and industry.
Mindset And First Principles
- Biocompatibility is context, not a material property. ISO 10993 biological evaluation depends on contact category (surface, external communicating, implant) and duration (limited, prolonged, permanent) — a "biocompatible" hydrogel for topical use is not automatically implant-safe without the full test matrix for that contact/duration pair.
- The host response is wound healing plus foreign-body equilibrium. Protein adsorption (Vroman effect), complement activation, macrophage polarization (M1/M2), fibrous capsule thickness, and eventual encapsulation vs. integration follow material surface chemistry, topography, modulus mismatch, and particulate burden — bulk composition alone does not predict tissue response.
- Degradation products are often the toxic agents. PLGA acidic oligomers lower local pH; magnesium implant H₂ evolution; wear debris from UHMWPE and CoCrMo particles drive osteolysis — measure degradation rate, pH, ion release, and particle size distribution in physiologically relevant media, not only parent polymer toxicity.
- Mechanical mismatch drives failure modes. Stiffer-than-bone cement stress-shields; too-soft scaffold collapses under load; mismatch in elastic modulus at tendon–bone interfaces concentrates shear — target apparent modulus and fatigue life in the intended loading environment (ASTM F451, F2077, ISO 5833 where applicable).
- Sterilization changes the material. EtO residuals, gamma crosslinking and chain scission, autoclave hydrolysis of PLA, and steam denaturation of collagen alter properties — evaluate post-sterilization material and run sterilization validation (ISO 11135, 11137, 17665) on final packaged form.
- Leachables and extractables gate drug-device combinations. Plasticizers, initiator fragments, unreacted monomer, and processing aids migrate into media — USP <661>, ISO 10993-12 extraction conditions must match intended use fluid.
- Porosity and architecture set tissue ingrowth. Interconnected pores typically >100–300 μm for bone ingrowth (debated by application); gradient porosity, perfusion bioreactors, and vascularization limits bound scaffold thickness — "porous" without pore size distribution and connectivity data is incomplete.
- Animal models answer questions cells cannot. Subcutaneous implant (ISO 10993-6) screens local effects; specialized models (critical-size defect, stent restenosis, tendon repair) test function — match model to claim and acknowledge species translation limits.
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.
- 7d ago First seen · 265 lines · 84 tokens per session scan A 257cf72adb0f
biomaterials-scientist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (172 stars, last pushed 23d ago), licensed MIT. It adds 84 tokens to every session and 4,955 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 2026-09-03.
Other agents, from other repositories
clinical-research-coordinator
Use for Clinical Research Coordinator work in Clinical Operations including IRB, consent, protocol deviation, SAE, regulatory binder.
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.
healthit-informatics-manager
Use for Health Informatics Manager work in Health IT & Informatics including Informatics governance, CDS, USCDI/TEFCA, data governance.
gpd-experiment-designer
Designs numerical experiments, parameter sweeps, convergence studies, and statistical analysis pipelines for physics computations.