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-oncologygit 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-oncology)<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-oncology"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-oncology/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-oncology"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-oncology.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 | $0.00025 | $0.00351 |
| Opus 5.5 | $0.00010 | $0.00140 |
| Sonnet 5.5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
spatial-oncology 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.
What it actually says
Spatial Oncology
Spatial Oncology maps cancer-related spatial ecosystems and summarizes tumor, immune, stromal, and outcome-associated research patterns.
Interface
Python API only. This skill is intentionally not registered for spatialclaw run or other CLI execution routing.
Research-Use Boundary
Outputs are exploratory and research-use only. They do not diagnose disease, predict individual patient outcomes, recommend treatment, or provide clinical decision support. Placeholder or fallback outputs must not be interpreted as validated clinical predictions.
Python API
from skills.spatial._lib.oncology import run_oncology
result = run_oncology(adata, method="tumor_ecosystem", cell_type_key="cell_type")
Capabilities
- Tumor core, edge, and interface mapping.
- Supervised niche discovery by condition.
- Exploratory cohort outcome association helpers.
- Response-associated spatial pattern summaries.
Validation
Covered by tests/spatial/test_library_only_skills.py::test_spatial_oncology_smoke.
What ships with it
1 file 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 · 54 lines · 25 tokens per session scan A cc44d9bcaa8e
spatial-oncology is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 351 once invoked, about $0.0001 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
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-cnv
Load when inferring copy-number variation per spot on a preprocessed spatial AnnData with chromosome-annotated genes via infercnvpy (default — log-ratio sliding-window) or Numbat (R, allele-aware clone deconvolution). Skip when var["chromosome"] / var["start"] / var["end"] gene-coord metadata is missing; no…
cancer-research
Deep cancer research skill for finding maximum life-extension treatment strategies. Use this skill whenever a user asks about cancer treatment options, cancer research, oncology treatment plans, survival optimization, clinical trials for cancer, immunotherapy options, or any query about extending life for a cancer…
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.