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 ma-compbio-lab/SkillFoundry --skill bcftools-variant-filtering-startergit clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundryWrote 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/ma-compbio-lab/skillfoundry/bcftools-variant-filtering-starter)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/bcftools-variant-filtering-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/bcftools-variant-filtering-starter.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 5.1 | $0.00000 | $0.00311 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
bcftools-variant-filtering-starter 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
bcftools Variant Filtering Starter
Use this skill to run a deterministic bcftools view filtering example on a tiny VCF and capture the kept variants in a compact JSON summary.
What it does
- Runs
bcftools viewwith a configurable include expression against a local VCF. - Writes a compressed filtered VCF plus a tabix index.
- Summarizes the input record count, passing record count, and kept IDs for testing and demos.
When to use it
- You need a runnable starter for VCF filtering logic.
- You want a tiny verified example before building cohort-scale post-calling workflows.
- You need a smoke-testable wrapper around
bcftoolsin the repo-managed genomics environment.
Example
python3 skills/genomics/bcftools-variant-filtering-starter/scripts/run_bcftools_variant_filtering.py \
--input skills/genomics/bcftools-variant-filtering-starter/examples/toy_variants.vcf \
--out scratch/genomics/bcftools_variant_filtering_summary.json \
--filtered-vcf-out scratch/genomics/toy_variants.filtered.vcf.gz
Verification
- Skill-local tests:
python3 -m unittest discover -s skills/genomics/bcftools-variant-filtering-starter/tests -p 'test_*.py' - Expected summary:
passing_record_count == 2andkept_ids == ["varA", "varC"]
What ships with it
10 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.
- assets/README.md 107 B
- assets/toy_variant_filtering_summary.json 485 B
- assets/toy_variants.filtered.vcf.gz 535 B
- assets/toy_variants.filtered.vcf.gz.tbi 106 B
- examples/README.md 114 B
- examples/toy_variants.vcf 314 B
- metadata.yaml 1.3 KB
- refs.md 290 B
- scripts/run_bcftools_variant_filtering.py 4.0 KB runs code
- tests/test_run_bcftools_variant_filtering.py 1.6 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.
- 4d ago First seen · 30 lines · 0 tokens per session scan A 57749c4de972
bcftools-variant-filtering-starter is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 311 tokens. 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
bim-validation-report
Generate comprehensive BIM model validation reports. Check data quality, completeness, and compliance with standards.
cluster-umap-layout-reproducibility-benchmarking
Use when you have executed an end-to-end SnapATAC2 pipeline on the pbmc10kmultiome dataset (or a similar single-cell ATAC-seq dataset with a published reference) and need to validate that spectral embedding, Leiden clustering, and UMAP layout have converged to expected cluster identities and.
computational-complexity-validation
Use when when an algorithm claims linear or sublinear time/space complexity (e.g., matrix-free spectral embedding) and you need to verify that claim holds for datasets at the scale intended (10 million+ cells).
checksum-verification-for-reproducibility
Use when you have executed a complex multi-step processing pipeline (e.g., ENCODE Hi-C uniform processing pipeline) and need to confirm that the generated output files match a known reference baseline.
end-to-end-bioinformatics-pipeline-testing
Use when after cloning or installing a peak-calling or genomic analysis tool from a repository, before using it on production data.
epic-array-simulation-benchmark
Use when when developing or validating a DNA methylation array analysis pipeline using ChAMP, you need an independent ground-truth dataset to confirm that DMR detection is working correctly.