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-population-geneticsgit 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-population-genetics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-population-genetics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-population-genetics/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-population-genetics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-population-genetics.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 | $0.00066 | $0.05584 |
| Opus 5.5 | $0.00026 | $0.02234 |
| Sonnet 5.5 | $0.00013 | $0.01117 |
| Haiku 4.5 | $0.00007 | $0.00558 |
Grade A, and why
tooluniverse-population-genetics 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Population Genetics Analysis
MC Strategy: Population genetics MC questions often test whether you know a specific theorem or result. COMPUTE the answer first (use popgen_calculator.py or write Python), then match to options. Don't try to reason about which option "sounds right."
Analyze population-level genetic variation, allele frequencies, GWAS associations, clinical significance, and evolutionary constraints using ToolUniverse tools.
When to Use
Activate this skill when the user asks about:
- Allele frequencies across populations (gnomAD, 1000 Genomes)
- GWAS associations for diseases/traits
- Clinical variant interpretation (ClinVar, VEP)
- Gene-level constraint metrics (pLI, LOEUF, o/e ratios)
- Selection, drift, linkage disequilibrium, or population structure
- Variant annotation and functional consequences
LOOK UP, DON'T GUESS
Query gnomAD/1000Genomes/GWAS Catalog FIRST for allele frequencies and associations. Preferred: use the PopGen_hwe_test, PopGen_fst, PopGen_inbreeding, and PopGen_haplotype_count tools for HWE, Fst, inbreeding, and haplotype calculations. Fallback: run popgen_calculator.py directly. For theoretical problems (delta-q, drift, LD decay), apply the formulas in the Theoretical Reasoning section below.
Tool Quick Reference
| Tool | Key Parameters | Notes |
|---|---|---|
gnomad_search_variants |
query (REQUIRED) |
Resolve rsID to variant_id format "CHR-POS-REF-ALT" |
gnomad_get_variant |
variant_id (REQUIRED), dataset |
Population frequencies. Default dataset: gnomad_r3; use gnomad_r4 for latest |
gnomad_get_gene_constraints |
gene_symbol (REQUIRED) |
pLI, o/e ratios. May timeout -- retry once |
MyVariant_query_variants |
query (REQUIRED) |
Aggregated: ClinVar + dbSNP + gnomAD + CADD. Uses hg19 coordinates |
EnsemblVEP_annotate_rsid |
variant_id (REQUIRED) |
Functional consequence, SIFT, PolyPhen. Param is "variant_id" NOT "rsid" |
EnsemblVEP_variant_recoder |
variant_id (REQUIRED) |
Convert between rsID/HGVS/VCF/SPDI |
gwas_get_snps_for_gene |
gene_symbol (REQUIRED) |
All GWAS SNPs for a gene |
gwas_search_associations |
query (REQUIRED) |
GWAS for a disease/trait (NOT gene name -- use gwas_get_snps_for_gene for genes) |
gwas_get_variants_for_trait |
trait (REQUIRED) |
Variants associated with a trait |
ClinVar_search_variants |
gene, condition, significance |
At least one filter required |
RegulomeDB_query_variant |
rsid (REQUIRED) |
Regulatory scoring (1a=strongest to 7=minimal) |
What ships with it
1 file 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 · 363 lines · 66 tokens per session scan A c4eca3d5f349
tooluniverse-population-genetics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,760 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 5,584 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.
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…