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-dose-responsegit 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-dose-response)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-dose-response"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-dose-response/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-dose-response"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-dose-response.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 | $0.00127 | $0.01628 |
| Opus 5 | $0.00063 | $0.00814 |
| Sonnet 5 | $0.00025 | $0.00326 |
| Haiku 4.5 | $0.00013 | $0.00163 |
Grade A, and why
tooluniverse-dose-response 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dose-Response / Concentration-Response Analysis
Turn paired concentration vs response measurements into a potency (IC50/EC50), a Hill slope, an efficacy (Emax), and a quality judgment — and compare potency between compounds.
When to use this
- Enzyme inhibition / activation assays, cell viability, reporter assays, radioligand binding, agonist/antagonist pharmacology.
- You have a list of concentrations and the response at each, and want IC50/EC50 + Hill slope.
- You want to say "compound A is N-fold more potent than B."
The model is the 4-parameter logistic (4PL) / Hill sigmoidal:
f(x) = Emin + (Emax − Emin) / (1 + (EC50/x)^n) — where n is the Hill slope.
Step 1 — Prepare the data (where results go wrong)
| Issue | What to do |
|---|---|
| Concentration units | Pick ONE unit (µM, nM, M) and use it for every point. The IC50 comes back in that unit. Don't mix. |
| Log vs linear concentrations | Pass concentrations on the linear scale (e.g. 0.01, 0.1, 1, 10), not log10. The fitter logs internally. |
| Zero/control concentration | Drop a literal 0 concentration (log(0) is undefined). Keep it only as the Emin/Emax reference if normalizing. |
| Direction | Inhibition curves go high→low (IC50); activation curves go low→high (EC50). The tools handle both; just be consistent. |
| Normalization | Convert raw signal to % of control if you want Emax/Emin near 100/0: % = 100 × (raw − blank)/(control − blank). Raw values also fit, but plateaus are then in raw units. |
| Replicates | Average technical replicates per concentration before fitting, or pass all points (the fit weights them equally). |
Coverage requirement: you need ≥4 points (the tools require it) and ideally 6–8 spanning both plateaus — points clearly above and clearly below the inflection. A curve that never plateaus gives an unreliable, extrapolated IC50 (see Step 4).
Step 2 — Fit / get the potency
Single curve → IC50 or EC50 (same math; "IC50" for inhibition, "EC50" for activation):
What ships with it
1 file 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.
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 · 79 lines · 127 tokens per session scan A b4a559d9ec12
tooluniverse-dose-response is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,628 once invoked, about $0.0006 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
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.
clip-dissect
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…