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-neurosciencegit 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-neuroscience)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-neuroscience"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-neuroscience/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-neuroscience"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-neuroscience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00095 | $0.06819 |
| Opus 5.5 | $0.00038 | $0.02728 |
| Sonnet 5.5 | $0.00019 | $0.01364 |
| Haiku 4.5 | $0.00010 | $0.00682 |
Grade A, and why
tooluniverse-neuroscience 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 10d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neuroscience Research Skill
KEY PRINCIPLES: LOOK UP, DON'T GUESS — use PubMed/EuropePMC for neuroanatomy facts, WormBase for C. elegans connectome data, UniProt for neural protein properties. Verify claims with literature before answering. Use Python computation for quantitative neuroscience problems.
LOOK UP, DON'T GUESS
When uncertain about any neuroscience fact — brain region function, neural circuit connectivity, ion channel properties, neurotransmitter receptor subtypes — SEARCH databases first. A PubMed-verified answer is always more reliable than reasoning from memory. This is especially critical for neuroanatomy, where structures have precise boundaries and connectivity patterns that are easy to confuse.
1. Computational Neuroscience Reasoning
Rate-Based Models
- Firing rate of a neuron: r = f(I - theta), where I = total synaptic input, theta = threshold, f = transfer function (sigmoid, ReLU, or threshold-linear)
- Balanced excitation/inhibition: in cortical networks, excitatory and inhibitory inputs are large but nearly cancel, leaving a small net drive
- Population rate equations: tau * dr/dt = -r + f(W*r + I_ext), where W = connectivity matrix
- Steady-state analysis: set dr/dt = 0, solve r = f(W*r + I_ext) — use fixed-point iteration or Newton's method
Integrate-and-Fire Neurons
- Membrane voltage dynamics: tau_m * dV/dt = -(V - V_rest) + R_m * I(t)
- When V reaches threshold V_th: emit spike, reset to V_reset, enter refractory period tau_ref
- Firing rate for constant input: r = 1 / (tau_ref + tau_m * ln((R_mI - V_reset) / (R_mI - V_th))) [valid when R_m*I > V_th]
- For sub-threshold input: neuron requires fluctuations (noise) to fire — noise-driven regime
- Key variants: LIF (leaky), EIF (exponential), AdEx (adaptive exponential), Izhikevich (2D with recovery variable)
Synaptic Plasticity
- STDP (Spike-Timing-Dependent Plasticity):
- Pre-before-post (positive dt): LTP (potentiation) — synapse strengthened
- Post-before-pre (negative dt): LTD (depression) — synapse weakened
- Window shape: typically exponential decay with tau_+ ~ 20ms (LTP) and tau_- ~ 20ms (LTD)
- Hebbian learning: "cells that fire together wire together" — correlation-based; unstable without normalization
- BCM theory: sliding threshold — low postsynaptic activity → LTD, high → LTP; threshold slides with average activity
- Homeostatic plasticity: synaptic scaling adjusts all synapses multiplicatively to maintain target firing rate
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.
- 10d ago Changed · +165 lines af9482c6b9a5
- 1mo ago Changed · +1 lines a8a530083620
- 1mo ago First seen · 191 lines · 95 tokens per session scan A fc55e7c1cb1a
tooluniverse-neuroscience is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 6,819 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
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.
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.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.