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-nfcore-pipelinesgit 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-nfcore-pipelines)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-nfcore-pipelines"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-nfcore-pipelines/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-nfcore-pipelines"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-nfcore-pipelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.03137 |
| Opus 5.5 | $0.00000 | $0.01255 |
| Sonnet 5.5 | $0.00000 | $0.00627 |
| Haiku 4.5 | $0.00000 | $0.00314 |
Grade A, and why
tooluniverse-nfcore-pipelines 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.
5. Download with `curl`/`wget` (URLs from step 4) or with `prefetch` + How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nf-core Pipeline Orchestration
Run real nf-core bioinformatics pipelines end-to-end for bench scientists who need alignment/quantification, variant calling, or chromatin-accessibility analysis without hand-building a pipeline.
Honesty contract (read first)
This skill drives real Nextflow pipelines on real compute. It must never fabricate a pipeline result.
- Preflight before anything. Run
scripts/check_environment.py. If Docker, Nextflow (>=23.04), or Java (>=11) is missing, print the install plan and STOP. Do not describe hypothetical alignment/variant-calling output. This skill cannot do useful work in a sandbox with no Docker daemon and no ability to install one — say so plainly instead of improvising a fake run. - Test profile is mandatory before real data. Every pipeline ships a
-profile testthat downloads a few MB of toy data and runs in minutes. It MUST pass before touching the user's real samples — it is the only way to know the environment actually works end-to-end (network egress, container pulls, resource limits) before a run that can take hours. - Never invent a pipeline version. nf-core pipelines are versioned and
pinned with
-r <version>. If you are not certain of the current stable release, tell the user to checkhttps://nf-co.re/<pipeline>/releasesrather than guessing a version number — the version numbers below were accurate at the time this skill was written but nf-core ships new releases regularly. - Confirm decision points with the user, do not silently default: pipeline choice, reference genome, and pipeline-specific options (aligner, variant-calling tools, read length). See Step 2 and Step 5.
- If you cannot run, say so. "Docker is not installed; here is the install plan" is the correct answer — never a made-up MultiQC summary or invented gene-count table.
When to use vs. not
Use this skill when the user wants to:
- Turn raw FASTQ (or BAM/CRAM) files into gene counts, called variants, or accessibility peaks by actually running an nf-core pipeline
- Reanalyze a public GEO/SRA dataset (GSE/GSM/SRR/SRX accession) from raw reads through to pipeline output
- Generate or validate an nf-core-format samplesheet
- Get help diagnosing a failed/stuck Nextflow run
What ships with it
8 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.
- references/geo_sra_acquisition.md 4.2 KB
- references/pipelines/atacseq.md 1.8 KB
- references/pipelines/rnaseq.md 1.8 KB
- references/pipelines/sarek.md 1.7 KB
- references/troubleshooting.md 2.7 KB
- scripts/check_environment.py 6.3 KB runs code
- scripts/detect_data_type.py 3.2 KB runs code
- scripts/generate_samplesheet.py 8.0 KB runs code
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 First seen · 294 lines · 0 tokens per session scan A 66fc29d080b0
tooluniverse-nfcore-pipelines is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,137 tokens. 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 2026-10-07.
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.
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…
aks-troubleshooting
Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation. WHEN: pod crashes or Pending, CrashLoopBackOff, OOMKilled, ImagePullBackOff, node NotReady, DNS or ingress failure, connectivity timeout, network policy, SNAT exhaustion, node-pool scaling blocked by QuotaExceeded or…
azure-cloud-migrate
Assess and migrate cross-cloud workloads to Azure with reports and code conversion. Supports Lambda→Functions, Beanstalk/Heroku/App Engine→App Service, Fargate/Kubernetes/Cloud Run/Spring Boot→Container Apps. WHEN: migrate Lambda to Functions, AWS to Azure, migrate Beanstalk, migrate Heroku, migrate App Engine, Cloud…
cloudron-app-packaging
Official Cloudron app packaging skill - Dockerfile patterns, manifest, addons, build methods.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.