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 TianGzlab/OmicsClaw --skill sc-integrate-clustergit 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/sc-integrate-cluster)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-integrate-cluster"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-integrate-cluster/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/tiangzlab/omicsclaw/sc-integrate-cluster"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-integrate-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00080 | $0.01057 |
| Opus 5 | $0.00040 | $0.00528 |
| Sonnet 5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
sc-integrate-cluster 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sc-integrate-cluster
Domain: Single-Cell Omics (scRNA) · Role: consensus member skill
When to use
One self-contained integrate + cluster unit, used as a fan-out member of
sc-consensus-integration (ADR 0016 / 0029). It produces a batch-correction
representation and clusters on it at a fixed resolution, emitting the standard
sc-clustering artifact schema so the consensus ScClusteringArtifactReader
reads it unchanged. You normally do not call this directly — the consensus
planner fans it out across methods. Input is a preprocessed AnnData with an obs
batch key (≥2 batches for any real integration method); an X_pca baseline is
computed if absent.
This is the single-cell analog of spatial-domains --method <m>: the integration
consensus fans out genuinely different batch-correction representations.
Inputs & Outputs
Inputs
- Modalities: scrna
- File types:
.h5ad - Requires a preprocessed AnnData (
Xnormalised, PCA/neighbours present)
Outputs
figure_data/embedding_points.csvfigure_data/clustering_summary.csvprocessed.h5adresult.json- Processed AnnData (
saves_h5ad) — addsobsm:X_pca
Flow
- Load the preprocessed AnnData; compute an
X_pcabaseline if absent. - Run the
--methodbackend to produceobsm[representation_used](X_pcafornone). - Build the neighbour graph on that representation and cluster with
--cluster-methodat the fixed--resolution. - Write
figure_data/embedding_points.csv+figure_data/clustering_summary.csvprocessed.h5ad+result.json.
Gotchas
processed.h5adcarries the member's integrated embedding — the consensus driver readsobsm[representation_used]from it to compute the integration intrinsic panel (ADR 0029). Do not strip obsm keys before the driver runs.result.json["representation_used"]records which embedding was used —X_pcafor--method none,X_<method>otherwise; the consensus reader keys off this rather than re-deriving it.- Fixed
--resolutionis by design — members must produce comparable cluster counts for the consensus operator; sweeping resolution belongs insc-consensus-clustering, not here. - scVI is GPU/stochastic — reproducible within tolerance, not bit-identical;
serialise GPU members (
--max-parallel 1at the consensus level).
What ships with it
5 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 · 109 lines · 80 tokens per session scan A b9bd5e812015
sc-integrate-cluster is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,057 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
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…
Virtual Embryo — atlas data + knowledge graph
Query the Virtual Embryo knowledge graph (mouse/human developmental biology: genes, anatomy, Theiler/Carnegie stages, gene expression, diseases, papers) and its 3D atlas catalog (anatomical OPT/light-sheet volumes + 3D spatial- transcriptomics datasets), and visualise those datasets in 3D with the volume3d / spatial3d…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
Single-Cell Analysis Skills Index
Core skills for single-cell RNA-seq analysis: quality control, cell type annotation, and trajectory inference. These are high-priority actionable workflows — load them first for common single-cell tasks.