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-annotatenpx skills add TianGzlab/OmicsClaw --skill spatial-annotategit 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-annotate)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/spatial-annotate"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/spatial-annotate.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 | $0.00071 | $0.01923 |
| Opus 5 | $0.00036 | $0.00962 |
| Sonnet 5 | $0.00014 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00192 |
Grade A, and why
spatial-annotate 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spatial-annotate
When to use
The user has a single-cell-per-spot spatial AnnData (Xenium / MERFISH / Slide-seq) OR wants a discrete per-spot label even for Visium and has either marker genes or a labelled scRNA reference. Four methods:
marker_based(default) — built-in marker dictionaries (--species,--marker-n-genes,--marker-padj-cutoff); optional custom marker model via--model. No reference needed.tangram— gradient mapping from a labelled scRNA reference (--tangram-num-epochs,--tangram-train-genes,--tangram-device). Requirestangram+torch.scanvi— scvi-tools scANVI semi-supervised classifier (--scanvi-n-hidden/--scanvi-n-latent/--scanvi-n-layers,--scanvi-max-epochs). Requiresscvi-tools+torch.cellassign— Bayesian probabilistic assignment with marker matrix (--cellassign-max-epochs).
For proportion deconvolution on Visium-style multi-cell spots use
spatial-deconv. For tissue domains use spatial-domains.
Inputs & Outputs
Inputs
- File types:
.h5ad - Requires a preprocessed AnnData (
Xnormalised, PCA/neighbours present) - Expects
obsm:spatial
Outputs
tables/annotation_cell_type_counts.csvtables/annotation_probabilities.csvtables/annotation_spatial_points.csvtables/annotation_summary.csvtables/annotation_umap_points.csvtables/cell_type_assignments.csvtables/cluster_annotations.csvtables/marker_overlap_scores.csvfigures/annotation_confidence_histogram.pngfigures/annotation_confidence_spatial.pngfigures/annotation_probability_heatmap.pngfigures/cell_type_barplot.pngfigures/cell_type_spatial.pngfigures/cell_type_umap.pngfigures/marker_overlap_heatmap.pngprocessed.h5adreport.mdresult.json- Processed AnnData (
saves_h5ad) — addsobs:cell_type;obsm:tangram_ct_pred,scanvi_probabilities,cellassign_probabilities
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.
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 · 146 lines · 71 tokens per session scan A bea087e528c6
spatial-annotate is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,923 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
spatial-cell-annotation
Cell type annotation for spatial transcriptomics data using marker-based scoring, Tangram mapping, scANVI transfer, or CellAssign probabilistic models.
spatial-deconvolution
Cell-type deconvolution for spatial transcriptomics by mapping a single-cell RNA-seq reference onto spatial data.
spatial-omics-integrate
Integrate two aligned spatial omics modalities on the same cells using SpatialGlue or SpaDDM. Standard input contract: --input --omics2 . Supports demo mode and validated modality pairs such as RNA+Protein and RNA+ATAC.
spatial-sc2spatial
Python API skill for mapping reference single-cell annotations and expression programs onto spatial transcriptomics data.
marker_panel_builder
Build positive and negative marker panels for a cell type or state and explain the confidence of the proposed panel.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…