ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
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.
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-computational-biophysicsgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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/skills/mims-harvard/tooluniverse/tooluniverse-computational-biophysics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-computational-biophysics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-computational-biophysics/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/skills/mims-harvard/tooluniverse/tooluniverse-computational-biophysics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-computational-biophysics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.04543 |
| Opus 5 | $0.00048 | $0.02271 |
| Sonnet 5 | $0.00019 | $0.00909 |
| Haiku 4.5 | $0.00010 | $0.00454 |
Grade A, and why
tooluniverse-computational-biophysics 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computational Biophysics & Quantitative Biology Skill
1. Recognize the Physical Process
The single most important step: identify what physical process the problem describes. In quantitative biology, almost every problem maps to one of these:
- Drug enters body → distributes → is eliminated: pharmacokinetics. Key quantities: dose, bioavailability, volume of distribution, clearance, half-life. The body is a compartment model.
- Radioactive tracer decays over time: nuclear medicine. Same math as drug elimination (exponential decay) but the rate constant is a physical property of the isotope, not a patient variable.
- Pathogen spreads through population: epidemiology. R₀ determines whether an epidemic grows or dies. Herd immunity threshold = 1 - 1/R₀. Every epidemic model starts here.
- Ligand binds receptor: binding equilibrium. At low [ligand], binding is linear. At saturation, all sites occupied. Kd = concentration at half-maximal binding. This same curve describes enzyme kinetics, drug-receptor occupancy, and surface adsorption.
- Contaminant enters environment: dilution + persistence. Two questions: what is the concentration after mixing (conservation of mass), and how long does it persist (exponential decay with environmental half-life)?
- Two populations differ genetically: population genetics. Fst measures differentiation. HWE tests if mating is random. Gene flow opposes drift.
- Neurons communicate in a network: computational neuroscience. Integrate-and-fire models, synaptic dynamics, balanced excitation/inhibition. Mean firing rate depends on input current relative to threshold.
Once you name the process, the mathematical structure follows. Solve algebraically first, substitute numbers second, and always check that units cancel correctly and the magnitude is physically reasonable.
2. Reasoning Patterns by Problem Type
These are not formulas. They are ways of thinking about what is happening physically.
Conservation / Dilution Problems
Something is being spread into a larger volume, or two streams are mixing. The total amount of substance is conserved. Think: amount_before = amount_after, where amount = concentration x volume. This covers serial dilutions, mixing streams, stock solution preparation, and environmental discharge into rivers.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/burn_fluids.py 12 KB runs code
- scripts/env_risk_assessment.py 9.1 KB runs code
- scripts/enzyme_kinetics.py 15 KB runs code
- scripts/epidemiology.py 28 KB runs code
- scripts/fluid_calculations.py 14 KB runs code
- scripts/herd_immunity.py 4.1 KB runs code
- scripts/iv_drip_rate.py 2.0 KB runs code
- scripts/mc_analyzer.py 14 KB runs code
- scripts/radioactive_decay.py 13 KB runs code
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 · 277 lines · 97 tokens per session scan A 2e9c51d09d8c
tooluniverse-computational-biophysics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 97 tokens to every session and 4,543 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 2026-08-30.
Other skills, from other repositories
dfam-check
Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
intermediate-outputs
Use this skill when working with circuit discovery in language models, mechanistic interpretability, activation patching, attribution patching, or Layer-wise Relevance Propagation (LRP) for neural network analysis.