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-network-pharmacologygit 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-network-pharmacology)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-network-pharmacology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-network-pharmacology/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-network-pharmacology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-network-pharmacology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00077 | $0.03322 |
| Opus 5.5 | $0.00031 | $0.01329 |
| Sonnet 5.5 | $0.00015 | $0.00664 |
| Haiku 4.5 | $0.00008 | $0.00332 |
Grade A, and why
tooluniverse-network-pharmacology 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 1mo 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COMPUTE, DON'T DESCRIBE
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.
Network Pharmacology Pipeline
Construct and analyze compound-target-disease (C-T-D) networks to identify drug repurposing opportunities, understand polypharmacology, and predict drug mechanisms using systems pharmacology approaches.
LOOK UP DON'T GUESS - Retrieve actual target lists, network data, and clinical evidence from tools. Do not infer network relationships from drug class alone.
IMPORTANT: Always use English terms in tool calls, even if the user writes in another language. Respond in the user's language.
Polypharmacology Reasoning (Start Here)
Before building any network, reason about what kind of multi-target effect you are dealing with:
A drug hitting multiple targets is either polypharmacology (desired multi-target) or promiscuity (undesired off-target). The distinction depends on whether the additional targets contribute to efficacy or cause toxicity.
Use this framework to guide the analysis:
- Desired polypharmacology: multiple targets all lie within the same disease module or pathway. Example: a kinase inhibitor that hits both EGFR and ERBB2 in the same signaling cascade. Look for pathway co-membership and disease module overlap. This is a network proximity argument.
- Off-target promiscuity: additional targets are in unrelated pathways, especially those associated with known toxicity (hERG for cardiotoxicity, CYP3A4 for drug interactions, COX-1 for GI toxicity). Look for these in the safety phase before claiming benefit.
- Repurposing hypothesis: the drug's known targets have strong genetic/functional evidence for the new disease. Network proximity (Z-score) quantifies this. A Z < -2 with p < 0.01 is meaningful signal; a Z near 0 means the targets are essentially unconnected to the disease module.
- Mechanism ambiguity: if a drug has 10+ known targets, do not treat all as therapeutically relevant. Start with primary mechanism-of-action targets, then ask whether secondary targets add to or subtract from the therapeutic window.
What ships with it
7 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.
- 1mo ago First seen · 206 lines · 77 tokens per session scan A 1722277f504a
tooluniverse-network-pharmacology is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 3,322 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 2026-09-03.
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.