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-translationnpx skills add ShangBioLab/SpatialClaw --skill spatial-translationgit 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-translation)<a href="https://agentmods.dev/skills/shangbiolab/spatialclaw/spatial-translation"><img src="https://agentmods.dev/badge/skills/shangbiolab/spatialclaw/spatial-translation.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 | $0.00025 | $0.00299 |
| Opus 5 | $0.00013 | $0.00150 |
| Sonnet 5 | $0.00005 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
spatial-translation 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 4d 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 Translation
Spatial Translation supports cross-modal prediction and virtual spatial modality generation.
Interface
Python API only. This skill is intentionally not registered for spatialclaw run or other CLI execution routing. Placeholder or synthetic predictions are for method prototyping and must not be interpreted as validated biological measurements.
Python API
from skills.spatial._lib.translation import run_translation
result = run_translation(adata, images=None, method="hist2st")
Capabilities
- Histology-to-expression prediction helpers.
- Histology-to-protein prediction helpers.
- Super-resolution reconstruction helpers.
- Cross-slice interpolation helpers.
Validation
Covered by tests/spatial/test_library_only_skills.py::test_spatial_translation_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.
- 4d ago First seen · 49 lines · 25 tokens per session scan A 873dfd0d57cc
spatial-translation is a skill published in the GitHub repository ShangBioLab/SpatialClaw (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 299 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
trident
Process whole-slide pathology images (WSIs) with TRIDENT: tissue segmentation, patch coordinate extraction, and patch/slide feature (embedding) extraction with foundation models (UNI, CONCH, Virchow, Gemma, Titan, GigaPath, etc.). Use when the user works with WSIs (.svs/.tiff/.ndpi/.mrxs/.czi/.dcm), mentions TRIDENT…
consensus-domains
Load when you want a verified multi-method consensus over spatial tissue domains on a preprocessed spatial AnnData — fanning out N domain methods, ranking base clusterings, and emitting a typed consensus with cross-method disagreement. Skip when one method suffices (use spatial-domains); the data is single-cell (use…
consensus-interpret
Load when biologically interpreting a finished verified consensus run (consensus-domains / sc-consensus-clustering) — inline DE, marker-DB lookup, and LLM cell-type naming with mandatory marker citations + evidence-bound next-step recommendations. Skip when the consensus run failed (fix it first); forward query→skill…
spatial-annotate
Load when assigning per-spot cell-type labels on a spatial AnnData via marker-gene scoring or scRNA-reference mapping (Tangram / scANVI / CellAssign). Skip when computing spot-level cell-type proportions for multi-cell-per-spot platforms (use spatial-deconv); tissue-domain detection (use spatial-domains).
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…
spatial-communication
Load when computing ligand-receptor cell-cell communication on a preprocessed spatial AnnData with obs[celltypekey] (default leiden) via LIANA (default), CellPhoneDB, FastCCC, or CellChat (R). Skip when running scRNA-only L-R inference (use sc-cell-communication); no cell-type labels exist (use spatial-annotate).