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 genomics-vcf-operationsgit 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/genomics-vcf-operations)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/genomics-vcf-operations"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/genomics-vcf-operations/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/genomics-vcf-operations"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/genomics-vcf-operations.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 | $0.00076 | $0.01137 |
| Opus 5 | $0.00038 | $0.00568 |
| Sonnet 5 | $0.00015 | $0.00227 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
genomics-vcf-operations 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genomics-vcf-operations
When to use
The user has a VCF (cohort, single-sample, or merged) and wants:
classify variants by type (SNP / MNP / INS / DEL / COMPLEX),
compute Ti/Tv on biallelic SNPs, optionally apply hard QUAL / DP
filters, and emit per-chromosome counts. This skill mirrors a
subset of bcftools stats + a simple QUAL/DP filter pass — pure
Python, no bcftools required.
For variant calling itself (BAM → VCF) see genomics-variant-calling;
for functional impact (gene / consequence / impact) use
genomics-variant-annotation.
Inputs & Outputs
Inputs
- File types:
.vcf - VCF structure:
##fileformat; columns:#CHROM,POS,ID,REF,ALT,QUAL,FILTER,INFO
Outputs
tables/variants.csvfiltered.vcfreport.mdresult.json- Produces artifact
genomics.filtered_variantsasfiltered.vcf(vcf)
Flow
- Load plain/gzip VCF (
--input <file.vcf[.gz]>) or generate a demo VCF atoutput_dir/demo.vcf. - Parse records; classify each ALT into SNP / MNP / INS / DEL / COMPLEX.
- Apply
--min-qualand--min-dpfilters; always materialise the declared normalizedfiltered.vcfartifact (zero thresholds are pass-through). - Compute Ti/Tv on biallelic SNPs; aggregate per-chromosome counts.
- Write
tables/variants.csv(genomics_vcf_operations.py:325) +report.md+result.json(:341).
Gotchas
--inputREQUIRED unless--demo.genomics_vcf_operations.py:310raisesValueError("--input required when not using --demo"); non-existent paths raiseFileNotFoundErrorat:313.- Plain
.vcfplus gzip/bzip2/xz-compressed VCF are supported. Unknown compression codecs are rejected by the content probe rather than passed to the parser. filtered.vcfis always emitted. With the default zero thresholds it is a normalized pass-through; positive--min-qual/--min-dpvalues reduce the retained records.- Multi-allelic rows are scored per-ALT but counted as one VCF line. Per-allele Ti/Tv is computed correctly, but downstream tools that count "rows" will under-count vs
bcftools view. Pre-normalise (bcftools norm -m -) for row-by-allele math. - DP is read from
INFO/DPonly. Per-sampleFORMAT/DP(genotype-level) is ignored — single-sample VCFs that only put DP in FORMAT will seeDP=NA, and--min-dpwill drop them all. - Demo VCF is a minimal SNV+indel set with random QUAL/DP. Useful for orchestrator smoke tests; not biologically meaningful.
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.
- 9d ago First seen · 92 lines · 76 tokens per session scan A 632dfdc66a35
genomics-vcf-operations is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,137 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 2026-08-30.
Other skills, from other repositories
biomcp
Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…
biomcp-research
Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.
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…
biological-expert
Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.
biotech-expert
Expert in biotechnology systems, genomics, LIMS, bioinformatics pipelines, lab automation, and bioprocess management. Use when the user mentions genomics, bioinformatics, LIMS, lab automation, bioprocessing, or gene sequencing, or when the task involves Genomics and Sequencing Technologies, Laboratory Information…
nfcore-scrnaseq-wrapper
Wrapper skill for running nf-core/scrnaseq 4.1.0 upstream single-cell RNA-seq preprocessing from FASTQ with strict preflight, reproducibility outputs, and downstream handoff to ClawBio scRNA skills.