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-filtergit 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-filter)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-filter"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-filter/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-filter"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-filter.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 | $0.00063 | $0.02011 |
| Opus 5.5 | $0.00025 | $0.00804 |
| Sonnet 5.5 | $0.00013 | $0.00402 |
| Haiku 4.5 | $0.00006 | $0.00201 |
Grade A, and why
sc-filter 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 17d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sc-filter
When to use
The user has reviewed sc-qc output and now wants to actually drop
low-quality cells and lowly-detected genes — by per-cell thresholds
(--min-genes, --max-genes, --max-mt-percent, --min-counts,
--max-counts, --min-cells) or tissue-specific presets (--tissue brain / pbmc / etc.). This skill removes cells; it does not
normalise, cluster, or annotate.
Use from a step
filtering = load_skill("sc-filter")
before = read_input("results/01_qc/intermediate/adata_qc.h5ad")
after = filtering.filter_cells(before, tissue="pbmc")
write_output(filtering.filter_summary(after), "tables/filter_summary.csv")
write_output(filtering.filter_stats_table(after), "tables/filter_stats.csv")
write_output(after, "intermediate/adata_filtered.h5ad")
Run doublet detection before filtering when doublets should be removed.
In the next preprocessing step, call
preprocess(after, apply_filters=False) to keep these cells and genes.
A complete demo step is in examples/example_step.py.
API
filter_cells(adata, *, min_genes: int=200, max_genes: int | None=None, min_counts: int | None=None, max_counts: int | None=None, max_mt_percent: float | None=20.0, min_cells: int=3, tissue: str | None=None, remove_doublets: bool=True, doublet_score_threshold: float=0.25)
Return a filtered copy of an AnnData, with counts and matrix contracts.
Existing QC columns are reused. Otherwise counts are selected from the input's counts layer, raw snapshot or X and missing QC metrics are computed. A normalized X with existing QC metrics is preserved. Doublet removal reads existing obs columns; it does not run doublet detection.
:param min_genes: Minimum detected genes per cell. Default 200. :param max_genes: Maximum detected genes per cell; None leaves it uncapped. :param min_counts: Minimum counts per cell; None disables this threshold. :param max_counts: Maximum counts per cell; None disables this threshold. :param max_mt_percent: Maximum mitochondrial percentage. Default 20.0; None disables the threshold. :param min_cells: Minimum retained cells expressing a gene. Default 3. :param tissue: Preset from tissue_presets(); overrides min_genes, max_genes and max_mt_percent. None uses the supplied thresholds. :param remove_doublets: Drop cells marked by predicted_doublet, or by doublet_score when the boolean column is absent. Default True. :param doublet_score_threshold: Score cutoff for the score-only case. Default 0.25. :returns: A new AnnData with retained cells and genes; run_info records effective thresholds, the count source and the filtering summary. :raises ValueError: Input requiring QC metrics has no count-like matrix.
What ships with it
9 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.
- _api.py 8.5 KB runs code
- examples/example_step.py 829 B runs code
- references/methodology.md 4.3 KB
- references/output_contract.md 1.5 KB
- references/parameters.md 1.0 KB
- references/r_visualization.md 545 B
- sc_filter.py 26 KB runs code
- tests/test_filter_api.py 1.9 KB runs code
- tests/test_sc_filter.py 3.2 KB runs code
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.
- 17d ago Changed · +85 lines 49f68133f980
- 1mo ago First seen · 108 lines · 63 tokens per session scan A c93c9b5eb57c
sc-filter is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 17d ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,011 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
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.
scRNA_qc_checklist
Turn single-cell RNA-seq summary metrics into a practical QC checklist with explicit assumptions and threshold recommendations.
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…
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-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…