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-plant-genomicsgit 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-plant-genomics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-plant-genomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-plant-genomics/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-plant-genomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-plant-genomics.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 | $0.00082 | $0.01995 |
| Opus 5.5 | $0.00033 | $0.00798 |
| Sonnet 5.5 | $0.00016 | $0.00399 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
tooluniverse-plant-genomics 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plant Genomics & Biology
Pipeline for investigating plant genes, metabolic pathways, species taxonomy, and comparative plant biology using ToolUniverse tools.
Reasoning Strategy
Plant genomes are large (wheat is ~17 Gb, vs. 3 Gb for human) and often polyploid — wheat is hexaploid (AABBDD), meaning there are three homeologous copies of most genes. When comparing plant genes to Arabidopsis, always account for whole-genome duplications: a single Arabidopsis gene may have 2–4 paralogs in a crop species, all potentially with diverged functions. Gene families are massively expanded in plants relative to animals (e.g., receptor-like kinases, cytochrome P450s, transcription factors) — a BLAST hit does not mean functional equivalence. Arabidopsis thaliana is the primary model, but its small genome and rapid life cycle mean some features (wood formation, nitrogen fixation symbiosis, C4 photosynthesis) are absent and must be studied in other species.
LOOK UP DON'T GUESS: Do not assume gene function by sequence similarity alone in polyploid species; look up functional validation evidence via UniProt (reviewed entries) or PlantReactome. Do not assume KEGG organism codes — use the table or query kegg_search_pathway with the species name to confirm availability.
Key principles:
- Plant-specific pathways — photosynthesis, secondary metabolism, hormone signaling are unique to plants
- PlantReactome as foundation — curated plant pathway database with cross-species coverage (Oryza, Arabidopsis, Zea mays, etc.)
- Ensembl Plants for genomics — use Ensembl with plant species names for gene lookup and annotation
- KEGG for metabolism — KEGG has plant-specific organism codes (ath=Arabidopsis, osa=rice, zma=maize)
- Evidence grading — T1: functional validation (mutant phenotype), T2: expression/localization data, T3: ortholog-based prediction, T4: computational annotation only
When to Use
- "What pathway is [plant gene] involved in?"
- "Find genes in the flavonoid biosynthesis pathway"
- "Compare [gene] across Arabidopsis and rice"
- "What species is [plant name]?"
- "Plant hormone signaling pathways"
- "Photosynthesis gene annotation"
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 Changed · +2 lines 5199cd262466
- 1mo ago First seen · 146 lines · 82 tokens per session scan A cdd431540ca6
tooluniverse-plant-genomics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 1,995 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.