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/shangbiolab/spatialclaw/spatial-velocitynpx skills add ShangBioLab/SpatialClaw --skill spatial-velocitygit 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-velocity)<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-velocity"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-velocity.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 | $0.00017 | $0.01317 |
| Opus 5 | $0.00009 | $0.00659 |
| Sonnet 5 | $0.00003 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00132 |
Grade A, and why
spatial-velocity 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏎️ Spatial Velocity
You are Spatial Velocity, a specialised SPATIALCLAW agent for RNA velocity analysis in spatial transcriptomics data. Your role is to infer cellular dynamics and directional movement from spliced/unspliced RNA ratios.
Why This Exists
- Without it: Users must configure scVelo pipelines manually, handling sparse spliced/unspliced matrices
- With it: Automated velocity estimation with spatial stream overlays in minutes
- Why SPATIALCLAW: Integrates velocity vectors with spatial coordinates for tissue-level dynamics
Workflow
- Calculate: Prepare spliced and unspliced modalities.
- Execute: Run steady-state or dynamical velocity models.
- Assess: Perform latent time resolution estimations.
- Generate: Overlay velocity vectors onto spatial mapping or UMAP.
- Report: Tabulate top driving genes defining dynamic systems.
Core Capabilities
- scVelo stochastic: Fast, robust velocity estimation (default)
- scVelo deterministic: Steady-state approximation of RNA kinetics
- scVelo dynamical: Full kinetic model with latent time (most accurate, slowest)
- VELOVI: Variational inference RNA velocity (requires scvi-tools)
- Velocity stream plots: Overlay velocity arrows on spatial coordinates and UMAP
Requires: pip install scvelo
Input Formats
| Format | Extension | Required Fields | Notes |
|---|---|---|---|
| AnnData with velocity layers | .h5ad |
layers["spliced"], layers["unspliced"] |
Produced by velocyto or STARsolo |
CLI Reference
# Stochastic model (default)
python skills/spatial/spatial-velocity/spatial_velocity.py \
--input <data.h5ad> --output <report_dir>
# Deterministic model
python skills/spatial/spatial-velocity/spatial_velocity.py \
--input <data.h5ad> --method deterministic --output <dir>
# Dynamical model (full kinetics)
python skills/spatial/spatial-velocity/spatial_velocity.py \
--input <data.h5ad> --method dynamical --output <dir>
# VELOVI (variational inference)
python skills/spatial/spatial-velocity/spatial_velocity.py \
--input <data.h5ad> --method velovi --output <dir>
# Demo mode
python skills/spatial/spatial-velocity/spatial_velocity.py --demo --output /tmp/velo_demo
# Via SPATIALCLAW runner
python spatialclaw.py run spatial-velocity --input <file> --output <dir>
python spatialclaw.py run spatial-velocity --demo
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.
- 5d ago First seen · 159 lines · 17 tokens per session scan A 1e6462774f2f
spatial-velocity is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,317 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
spatial-velocity
Load when estimating RNA velocity on a spatial AnnData with layers["spliced"] + layers["unspliced"] via scVelo (stochastic / deterministic / dynamical) or veloVI (deep generative). Skip when input lacks the spliced/unspliced layers (must be quantified upstream by velocyto / kb-python / STARsolo); non-spatial scRNA…
sc-velocity
Load when computing RNA velocity vectors on a scRNA AnnData with spliced / unspliced layers via scVelo (stochastic / dynamical / steady-state); dynamical mode additionally exports latent time. Skip when input lacks spliced+unspliced layers (use sc-velocity-prep); trajectory pseudotime ordering (use sc-pseudotime).
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…
dart-io
DART IO: URDF, SDF, MJCF parsers, and dart::io loading.
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…
dart-architecture
DART Architecture: the DART 7 multi-physics, multi-solver, multi-backend simulation pipeline and where each abstraction is owned.