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-noncoding-rnagit 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-noncoding-rna)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-noncoding-rna"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-noncoding-rna/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-noncoding-rna"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-noncoding-rna.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 | $0.00100 | $0.04308 |
| Opus 5.5 | $0.00040 | $0.01723 |
| Sonnet 5.5 | $0.00020 | $0.00862 |
| Haiku 4.5 | $0.00010 | $0.00431 |
Grade A, and why
tooluniverse-noncoding-rna scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.get(url, timeout=60) How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Non-Coding RNA Analysis
Pipeline for identifying, annotating, and interpreting non-coding RNAs and their biological roles. Covers microRNAs (miRNAs), long non-coding RNAs (lncRNAs), and other ncRNA classes.
Key principles:
- Class determines function — miRNAs repress mRNA translation; lncRNAs have diverse mechanisms (scaffolds, guides, decoys, enhancers); rRNAs/tRNAs are structural
- Targets matter more than the ncRNA itself — for miRNAs, the regulated mRNA targets determine the phenotype
- Expression context is critical — ncRNAs are highly tissue/cell-type specific
- Conservation indicates function — deeply conserved ncRNAs (miR-let-7, MALAT1) have well-established roles
- Evidence grading — T1: validated targets (reporter assay, CLIP-seq), T2: high-confidence computational prediction, T3: expression correlation, T4: sequence-based prediction only
Type-based reasoning — look up, don't guess: Non-coding RNA function depends on type: miRNA silences target mRNAs (look up targets in miRTarBase/TargetScan), lncRNA has diverse functions (scaffolding, guiding, decoying — check literature for the specific lncRNA), circRNA may sponge miRNAs.
For any ncRNA query: first identify the class from the name/sequence, then select the appropriate evidence source. Do not assume function based on name alone — a gene named "LINC" may have a characterized mechanism, or none at all. Always search PubMed for the specific ncRNA before interpreting. For miRNAs, validated targets (T1) from miRTarBase outweigh any computational prediction — a predicted target with no experimental support is a hypothesis, not a finding. For lncRNAs, mechanism is almost always determined by experimental studies; use PubMed_search_articles with the lncRNA name + "mechanism" or "function" to find relevant evidence. For circRNAs, miRNA sponging is the most common proposed mechanism but is frequently over-claimed — look for CLIP-seq or reporter assay evidence before asserting it.
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 · +40 lines fb05fd67d317
- 1mo ago First seen · 257 lines · 100 tokens per session scan A b31a09c59ad5
tooluniverse-noncoding-rna is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 4,308 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.