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 agentmods add skills/tiangzlab/omicsclaw/spatial-raw-processingnpx skills add TianGzlab/OmicsClaw --skill spatial-raw-processinggit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote 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/tiangzlab/omicsclaw/spatial-raw-processing)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/spatial-raw-processing"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/spatial-raw-processing.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01764 |
| Opus 5 | $0.00035 | $0.00882 |
| Sonnet 5 | $0.00014 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00176 |
Grade A, and why
spatial-raw-processing 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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spatial-raw-processing
When to use
The user has paired-end spatial-transcriptomics FASTQ files (read1 =
spatial barcode + UMI, read2 = cDNA) plus a STAR genome index, and
wants the standard ST-Pipeline run that produces a raw_counts.h5ad
with one row per spatial spot. Single backend: st_pipeline (calls
run_stpipeline from skills/spatial/_lib/stpipeline_adapter.py).
After this skill, chain to spatial-preprocess for QC + normalisation.
For non-spatial scRNA FASTQ use sc-fastq-qc. For bulk RNA-seq read
QC use bulkrna-read-qc.
Inputs & Outputs
Inputs
- Input kinds:
file,directory - Modalities: visium, slideseq
- File types:
.fastq,.fq,.json,.yaml,.yml - FASTQ structure: valid first record;
pairedlayout - Directory layouts (any):
paired-fastq
Outputs
tables/gene_qc.csvtables/raw_gene_qc.csvtables/raw_processing_run_summary.csvtables/raw_processing_spatial_points.csvtables/raw_spot_qc.csvtables/raw_top_genes.csvtables/run_summary.csvtables/saturation_curve.csvtables/spatial_coordinates.csvtables/spot_qc.csvtables/stage_summary.csvtables/top_genes.csvfigures/raw_detected_genes_spatial.pngfigures/raw_spot_qc_histograms.pngfigures/raw_top_genes_barplot.pngfigures/raw_total_counts_spatial.pngfigures/st_pipeline_saturation_curve.pngfigures/st_pipeline_stage_attrition.pngomicsclaw_stpipeline_run.jsonraw_counts.h5adst_pipeline.stderr.txtst_pipeline.stdout.txtreport.mdresult.json- Processed AnnData (
saves_h5ad) — addsobs:barcode,x_array,y_array;obsm:spatial
Flow
- Parse args (or load bundle JSON / YAML from positional
--input). _apply_effective_defaultsfills missing parameter values (threads, trimming, UMI ranges, etc.)._validate_real_run_bundle: checkread1/read2/ids/ref-mapexist and are well-typed; reject duplicate read1=read2; verify FASTQ extension.- Call
run_stpipeline(...)which shells out to ST-Pipeline (requires thestpipelinebinary on PATH or--stpipeline-repo+--bin-path). - Wrap the resulting count matrix into AnnData with
X = raw_counts,layers["counts"],raw = raw_counts_snapshot. - Save
raw_counts.h5adandresult.json. Print "next: spatial-preprocess on raw_counts.h5ad".
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.
- r_visualization/raw_processing_publication_template.R 3.5 KB
- r_visualization/README.md 1.4 KB
- references/methodology.md 7.6 KB
- references/output_contract.md 3.7 KB
- references/parameters.md 2.1 KB
- skill.yaml 4.3 KB
- spatial_raw_processing.py 12 KB runs code
- tests/test_spatial_raw_processing.py 3.4 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.
- yesterday First seen · 135 lines · 70 tokens per session scan A 09724602929f
spatial-raw-processing is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,764 once invoked, about $0.0003 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
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…
spatial-transcriptomics-spatial-data-io
Load spatial transcriptomics data from Visium, Xenium, MERFISH, Slide-seq, and other platforms using Squidpy and SpatialData. Use this skill when: (1) Loading Visium spatial transcriptomics data from Space Ranger output, (2) Loading Xenium single-cell resolution spatial data, (3) Loading MERFISH, CosMx, or other…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
data-stats-analysis
Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).