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-drug-target-validationgit 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-drug-target-validation)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-drug-target-validation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-target-validation/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-drug-target-validation"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-target-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 22 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00082 | $0.04235 |
| Opus 5 | $0.00041 | $0.02117 |
| Sonnet 5 | $0.00016 | $0.00847 |
| Haiku 4.5 | $0.00008 | $0.00424 |
Grade A, and why
tooluniverse-drug-target-validation 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug Target Validation Pipeline
Validate drug target hypotheses using multi-dimensional computational evidence before committing to wet-lab work. Produces a quantitative Target Validation Score (0-100) with priority tier classification and GO/NO-GO recommendation.
Reasoning Before Searching
A valid drug target must pass 4 gates in order. Failing an early gate makes later gates irrelevant:
- Genetic evidence linking it to disease: Does human genetic data (GWAS, rare variant studies, Mendelian genetics) support this target's role? Genetic evidence is the strongest predictor of clinical success. Use OpenTargets and GWAS catalog before anything else. If no genetic link exists, the hypothesis is speculative — document this clearly.
- Druggability: Can a molecule reach and modulate the target? Check structure availability (PDB, AlphaFold), binding pocket prediction (ProteinsPlus), target class (kinase, GPCR, nuclear receptor = favorable; transcription factor, scaffold protein = difficult), and existing chemical probes.
- Safety — essentiality in normal tissue: Is the target expressed in critical tissues (heart, liver, bone marrow)? Is knockout lethal in mice? High expression in essential tissue or lethality in mouse models is a strong safety red flag even before any clinical data.
- Competitive landscape: Are other drugs already approved or in late-stage trials for this target? If so, the bar is differentiation, not first-in-class. Check ChEMBL, DrugBank, and ClinicalTrials.gov early.
Do not proceed to Phase 3 (Chemical Matter) before completing Phase 1 (Disease Association). Gate 1 failures should prompt a NO-GO or pivot recommendation.
LOOK UP DON'T GUESS: Never assume a target is druggable based on its protein family alone, never assume expression is low in a tissue without checking GTEx or HPA, never assume no competitors without searching ClinicalTrials.gov.
RUN THE ML MODELS, DON'T SKIP THEM: When deep-learning predictors are available (ADMET-AI, ESMFold, AlphaFold, DoGSite, DynaMut2, DeepGO), run them even when database lookups or experimental data already cover the same property. The ML predictions provide an orthogonal, mechanistically-grounded estimate that's a first-class output of this skill — not a fallback. A target-validation report missing ML predictions is incomplete regardless of how much database evidence is present.
What ships with it
4 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.
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 · 286 lines · 82 tokens per session scan A ff83beacdfc5
tooluniverse-drug-target-validation is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 4,235 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 2026-08-30.
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.