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 aristoteleo/PantheonOS --skill upstream_processinggit clone --depth 1 https://github.com/aristoteleo/PantheonOSWrote 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/aristoteleo/pantheonos/upstream_processing)<a href="https://agentmods.dev/skills/aristoteleo/pantheonos/upstream_processing"><img src="https://agentmods.dev/badge/skills/aristoteleo/pantheonos/upstream_processing/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/aristoteleo/pantheonos/upstream_processing"><img src="https://agentmods.dev/badge/skills/aristoteleo/pantheonos/upstream_processing.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 | $0.00040 | $0.00510 |
| Opus 5.5 | $0.00016 | $0.00204 |
| Sonnet 5.5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
Upstream Processing Skills Index 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream Processing Skills
Skills and workflows for upstream data processing steps that precede standard single-cell analysis (QC, normalization, clustering, etc.). These cover technology-specific pipelines from raw sequencing data to analysis-ready count matrices with spatial coordinates.
Available Skills
OpenST
Open-ST is an open-source spatial transcriptomics technology that captures transcriptome-wide data at sub-cellular resolution. The computational pipeline covers flow cell barcode preprocessing, transcriptomic alignment via spacemake, image-to-coordinate registration, cell segmentation, and 3D reconstruction.
Skill directory: openst/
When to use:
- Processing raw Open-ST data from BCL files to spatially-resolved h5ad
- Aligning transcriptomic coordinates to H&E tissue images
- Cell segmentation and transcript-to-cell assignment
- 3D reconstruction from serial tissue sections
nf-core Pipelines
nf-core is a community-driven collection of 143+ curated Nextflow pipelines for bioinformatics. Skills cover installation, configuration, and pipeline-specific guides for transcriptomics, spatial omics, epigenomics, and variant calling.
Skill directory: nfcore/
When to use:
- Processing scRNA-seq data (10x, Drop-seq, Smart-seq) with nf-core/scrnaseq
- Processing spatial transcriptomics (Visium, Xenium, MERSCOPE) with nf-core pipelines
- Processing bulk RNA-seq, ATAC-seq, ChIP-seq, CUT&Run, or methylation data
- Variant calling from WGS/WES with nf-core/sarek
- Setting up Nextflow and nf-core on HPC clusters or cloud environments
Using Skills
- Identify your technology: Find the relevant sub-directory for your spatial/sequencing platform
- Load skill files: Read the full skill documents for step-by-step guidance
- Follow the pipeline: Upstream processing is sequential; follow stages in order
- Proceed to downstream analysis: After generating the count matrix, use the main omics skills for QC, clustering, etc.
What ships with it
10 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.
- nfcore/nfcore_dynamic_discovery.md 8.6 KB
- nfcore/nfcore_epigenomics.md 9.5 KB
- nfcore/nfcore_hic.md 9.7 KB
- nfcore/nfcore_spatial.md 7.4 KB
- nfcore/nfcore_transcriptomics.md 8.4 KB
- nfcore/nfcore_usage.md 8.0 KB
- nfcore/nfcore_variant_calling.md 7.4 KB
- nfcore/SKILL.md 4.7 KB
- openst/openst_computational.md 19 KB
- openst/SKILL.md 1.3 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.
- 1mo ago First seen · 59 lines · 40 tokens per session scan A 544d73fbdf25
Upstream Processing Skills Index is a skill published in the GitHub repository aristoteleo/PantheonOS (490 stars, last pushed today), licensed BSD-2-Clause. It adds 40 tokens to every session and 510 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.