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-epigenomicsgit 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-epigenomics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-epigenomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-epigenomics/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-epigenomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-epigenomics.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 | $0.00112 | $0.02760 |
| Opus 5 | $0.00056 | $0.01380 |
| Sonnet 5 | $0.00022 | $0.00552 |
| Haiku 4.5 | $0.00011 | $0.00276 |
Grade A, and why
tooluniverse-epigenomics 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 11d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genomics and Epigenomics Data Processing
⚠️ TOP-OF-MIND RULE: long-format methylation CSV — count ROWS, not unique positions
When the input is a long-format methylation CSV (one row per (sample, CpG_position)
e.g. columns Pos, Chromosome, MethylationPercentage), "how many sites are
removed when filtering" almost always means rows removed, NOT unique-position
removals. The two answers differ by a factor of ≈ n_samples.
| Question phrasing | What it means |
|---|---|
| "how many sites are removed when filtering …" | rows removed (= samples × positions failing the filter) |
| "how many unique CpG sites pass filter" | unique positions (dedupe by Pos then filter) |
❌ WRONG: df.drop_duplicates(["Pos"]).query("MethylationPercentage<10 or >90") then len(filtered) → counts unique positions (typically 100–1500)
✅ RIGHT: df.query("MethylationPercentage<10 or MethylationPercentage>90") then len(df) - len(filtered) → counts rows (typically 10k–30k)
If your answer is < 2000 when the data has 1000+ positions × 20+ samples, you deduplicated too early. Re-read the question's noun before reporting.
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).
Production-ready skill combining Python computation (pandas, scipy, numpy, pysam, statsmodels) with ToolUniverse annotation tools for epigenomics analysis.
What ships with it
6 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.
- 11d ago First seen · 204 lines · 112 tokens per session scan A 350408fa0ad6
tooluniverse-epigenomics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 2,760 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dfam-check
Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
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.
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.
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.