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-researchgit 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-research)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-drug-research"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-research/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-research"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-drug-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00071 | $0.03411 |
| Opus 5.5 | $0.00028 | $0.01364 |
| Sonnet 5.5 | $0.00014 | $0.00682 |
| Haiku 4.5 | $0.00007 | $0.00341 |
Grade A, and why
tooluniverse-drug-research 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 20d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drug Research Strategy
Comprehensive drug investigation using 50+ ToolUniverse tools across chemical databases, clinical trials, adverse events, pharmacogenomics, and literature.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Compound disambiguation FIRST - Resolve identifiers before research
- Citation requirements - Every fact must have inline source attribution
- Evidence grading - Grade claims by evidence strength (T1-T4)
- Mandatory completeness - All sections must exist, even if "data unavailable"
- English-first queries - Always use English drug/compound names in tool calls, even if the user writes in another language. Only try original-language terms as a fallback. Respond in the user's language
LOOK UP, DON'T GUESS
When asked about a drug, query ChEMBL/PubChem/DailyMed FIRST. Don't guess at mechanism, targets, or side effects — look them up. When you're not sure about a fact, your first instinct should be to SEARCH for it using tools, not to reason harder from memory.
Drug Mechanism Reasoning
When investigating a drug's mechanism of action, trace the full causal chain:
- Target engagement - Which protein(s) does the drug bind, and with what affinity/selectivity?
- Molecular effect - Does binding inhibit, activate, or modulate the target's function?
- Pathway consequence - Which signaling or metabolic pathway is altered downstream?
- Cellular phenotype - What changes occur at the cell level (proliferation, apoptosis, secretion)?
- Physiological outcome - How does the cellular effect translate to the therapeutic benefit in the patient?
Workflow Overview
1. Report-First Approach (MANDATORY)
DO NOT show the search process or tool outputs to the user. Instead:
- Create the report file FIRST -
[DRUG]_drug_report.mdwith all 11 section headers and[Researching...]placeholders. See REPORT_TEMPLATE.md for the full template. - Progressively update the report - Replace placeholders with findings as you query each tool.
- Use ALL relevant tools - Query multiple databases for each data type; cross-reference across sources.
What ships with it
5 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.
- 20d ago Changed · +7 lines 9e61fb08ba3b
- 1mo ago First seen · 245 lines · 71 tokens per session scan A 6cd5ca394515
tooluniverse-drug-research is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,760 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 3,411 once invoked, about $0.0003 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 2026-08-30.
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.
simulation-orchestrator
Orchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hypercube sampling), initialize and track batch job campaigns, monitor job completion status, and aggregate results with summary statistics across all runs. Use when running a parameter study across dt, kappa, or…
ontology-explorer
Parse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with domain/range, search for ontology terms by keyword, and parse or summarize raw OWL/XML files. Currently supports CMSO and ASMO…
hpc-runtime-doctor
Diagnose HPC runtime and scheduler problems for materials simulations, including MPI/OpenMP/GPU layout, modules, CUDA/Kokkos hints, scratch paths, walltime, job arrays, restart strategy, scheduler portability, and resource mismatch. Use when an ALREADY-SUBMITTED job failed, ran slowly, got killed, or behaved…
simulation-failure-triage
First-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signature (nonconvergence, NaN/Inf, exploding energy, unstable timestep, pressure blow-up, missing potentials/pseudopotentials, memory exhaustion, process crash/segfault, corrupted output, incomplete runs) and…