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-variant-analysisgit 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-variant-analysis)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-variant-analysis"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-variant-analysis/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-variant-analysis"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-variant-analysis.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 | $0.00077 | $0.06497 |
| Opus 5 | $0.00039 | $0.03248 |
| Sonnet 5 | $0.00015 | $0.01299 |
| Haiku 4.5 | $0.00008 | $0.00650 |
Grade A, and why
tooluniverse-variant-analysis 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 7d 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Variant Analysis and Annotation
RULE ZERO — Check for pre-computed results FIRST
Before following any instruction below, scan the data folder for:
*_executed.ipynb→ read withtu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'and cite its cell outputs as the authoritative answer- Pre-computed result files (CSV/TSV with names like
*results*,*deseq*,*enrich*,*stats*,*_simplified.csv) → read directly and report the requested value - Canonical analysis scripts (
analysis.R,run_*.py,find_*.R,*.Rmd) → execute as-is and read the output
Only follow this skill's re-analysis recipe below if none of the above exist. Re-running from raw data produces different numbers than the published answer and is much slower (often 5-10× turn count).
PRIMARY SCRIPTS — use these FIRST
These bundled scripts encode the question-specific gotchas (denominator
choices, ploidy defaults, multi-allelic split, multi-row Excel headers,
non-coding allowlist). They emit labelled KEY=VALUE lines that are
easier to parse than ad-hoc pandas/awk output. Prefer them over writing
new code.
| Script | When to use it |
|---|---|
gatk_haplotypecaller_pipeline.py |
Any "how many SNPs / indels were called by HaplotypeCaller from the BAM" question. Handles BWA index → align → sort → index → HaplotypeCaller, OR can start from an existing BAM (skip alignment), OR only count an existing VCF. Default --ploidy 2 (matches GATK's own default — most "called by HaplotypeCaller" GTs were generated with this). Pass --ploidy 1 for explicit haploid prokaryote calling. Multi-allelic split + bcftools-style SNP/indel detection is built in. |
coding_variant_filter.py |
"Average number of CHIP / coding variants per sample after filtering out intronic, intergenic, and UTR variants." Two-stage canonical filter: (1) drop Zygosity == Reference rows (when present — these inflate counts ~10×), (2) drop intronic/intergenic/UTR/upstream/downstream SO terms. Handles 2-row VarSeq Excel headers and per-sample folders or combined CSVs. |
variant_fraction.py |
"Fraction of variants with VAF < X annotated as Y" — denominator is the CODING subset only (synonymous/missense/splice_region/stop_gained/lost/start_lost/frameshift/inframe indel), NOT all records. |
What ships with it
15 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.
- .env.template 499 B
- python_implementation.py 64 KB runs code
- QUICK_START.md 9.9 KB
- references/annotation_guide.md 13 KB
- references/mutation_classification_guide.md 8.9 KB
- references/sv_cnv_analysis.md 16 KB
- references/vcf_filtering.md 8.0 KB
- scripts/annotate_variants.py 5.7 KB runs code
- scripts/coding_variant_filter.py 11 KB runs code
- scripts/filter_variants.py 8.7 KB runs code
- scripts/gatk_haplotypecaller_pipeline.py 14 KB runs code
- scripts/parse_vcf.py 5.6 KB runs code
- scripts/variant_fraction.py 4.8 KB runs code
- test_data/cohort2.vcf 2.3 KB
- test_data/sample.vcf 6.0 KB
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.
- 7d ago First seen · 503 lines · 77 tokens per session scan A 966edcda4d9d
tooluniverse-variant-analysis is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 6,497 once invoked, about $0.0004 per session on Opus 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
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.
astro-dso-doc
Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…
intermediate-outputs
Use this skill when working with circuit discovery in language models, mechanistic interpretability, activation patching, attribution patching, or Layer-wise Relevance Propagation (LRP) for neural network analysis.
clip-dissect
Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what…