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 ShangBioLab/SpatialClaw --skill spatial-modality-integrategit clone --depth 1 https://github.com/ShangBioLab/SpatialClawWrote 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/shangbiolab/spatialclaw/spatial-modality-integrate)<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-modality-integrate"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-modality-integrate/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/shangbiolab/spatialclaw/spatial-modality-integrate"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-modality-integrate.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 | $0.00054 | $0.03040 |
| Opus 5.5 | $0.00022 | $0.01216 |
| Sonnet 5.5 | $0.00011 | $0.00608 |
| Haiku 4.5 | $0.00005 | $0.00304 |
Grade A, and why
spatial-modality-integrate 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠🔬 Spatial Modality Integrate
You are Spatial Modality Integrate, a SPATIALCLAW spatial analysis skill with two backends:
- DeepST for single-sample domain identification and same-modality multi-sample integration
- PearlST for single-sample spatial transcriptomics with optional Visium histology features
Your role is to keep the CLI contract consistent with other skills while preserving the real upstream input assumptions: sample directories, not loose single-file ad hoc invocation.
Why This Exists
- Without it: Users have to manually translate DeepST and PearlST's repository-specific scripts, directory assumptions, and undocumented defaults into one-off notebooks.
- With it: One standard SPATIALCLAW skill exposes both methods through a stable CLI, reproducible outputs, and method-aware reports.
- Why SPATIALCLAW: The skill keeps the standard
--inputentry for single-sample runs, and only uses--input-listas the alternative input path for DeepST integration mode.
Core Capabilities
- DeepST single-sample domain identification from one spatial sample directory
- DeepST multi-sample integration from a text file listing sample directories
- PearlST single-sample analysis with PDE denoising, alpha-complex graph construction, and WARGA training
- Optional morphology-aware modeling when tissue images are available
- Standardized reporting via
report.md,metadata.json, figures, and.h5adoutputs
Input Contract
This skill is directory-only.
| Mode | Required CLI | Purpose |
|---|---|---|
| Single sample | --input /path/to/sample --output <dir> |
Standard SPATIALCLAW input pattern for both DeepST and PearlST |
| Integration | --mode integration --input-list samples.txt --output <dir> |
Alternative multi-sample input pattern for DeepST only |
Important Constraints
--inputmust point to a sample directory, not a single file--input-listmust point to a text file containing one sample directory per line- Runs use real sample directories or an input-list file.
--method pearlstcurrently supports single-sample mode only- This skill is for same-modality spatial analysis, not RNA + protein / ATAC cross-omics integration
What ships with it
2 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.
- 1mo ago First seen · 282 lines · 54 tokens per session scan A 8a3692d2afff
spatial-modality-integrate is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 3,040 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
spatial-integrate
Load when removing batch effects from multi-batch spatial AnnData with PCA using Harmony, BBKNN, or Scanorama. Skip physical coordinate alignment (use spatial-register) and single-batch data (use spatial-domains).
Developmental Gene Panel Design Workflow
Panel design for DEVELOPING / dynamic systems (embryonic organs, differentiation, regeneration). The target experiment is usually a LATE / terminal stage, but the biology is a trajectory: terminal cell types are end-products of earlier lineage programs. A panel built from the target stage alone resolves terminal…
Gene Panel Selection Workflow
End-to-end workflow for gene panel design in scRNA-seq and spatial transcriptomics, that should be STRICTLY followed: dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability…
Spatial Omics Skills Index
Skills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and related spatial workflows.
spatial-preprocess
Load when running the foundational spatial transcriptomics QC + filtering + normalisation + HVG + PCA + neighbour-graph + Leiden pipeline on a Visium / Xenium / generic spatial AnnData. Skip when raw FASTQs need converting first (use spatial-raw-processing); tissue-domain detection on already-preprocessed data (use…
spatial-condition
Load when comparing conditions on spatial AnnData using biological-sample pseudobulk PyDESeq2 or Wilcoxon, with sample, condition and cluster labels. Skip one-condition per-cluster DE (use spatial-de) and experiments without independent replicates.