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/tiangzlab/omicsclaw/genomics-phasingnpx skills add TianGzlab/OmicsClaw --skill genomics-phasinggit 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-phasing)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/genomics-phasing"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/genomics-phasing.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 | $0.00077 | $0.01128 |
| Opus 5 | $0.00039 | $0.00564 |
| Sonnet 5 | $0.00015 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
genomics-phasing 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
genomics-phasing
When to use
The user has a phased VCF (from WhatsHap, SHAPEIT5, Eagle2, etc.)
and wants phasing QC: total het count, phased fraction, phase-block
count, phase-block N50 (in bp), per-block sizes. Phasing detection
relies on the PS (Phase Set) FORMAT field plus pipe-delimited
genotype encoding (0|1 vs 0/1).
This skill does NOT phase variants — it summarises a VCF that has already been phased.
Inputs & Outputs
Inputs
- File types:
.vcf - Accepts artifact
genomics.filtered_variants(vcf)
Outputs
tables/phase_blocks.csvtables/phased_variants.csvreport.mdresult.json- Produces artifact
genomics.phased_variantsastables/phased_variants.csv(csv)
Flow
- Load VCF (
--input <phased.vcf>) or generate a demo phased VCF atoutput_dir/demo_phased.vcfwith--n-variantsrecords (genomics_phasing.py:200). - Parse records; classify each het as phased (
|in GT andPSpopulated) or unphased (/). - Group phased variants by
PS; compute per-block start / end / length / variant count. - Compute phase-block N50 (bp); phased fraction across all hets.
- Write
tables/phased_variants.csv(genomics_phasing.py:327) +tables/phase_blocks.csv(:345) +report.md+result.json(:348).
Gotchas
- No phaser is invoked. This skill ingests an already-phased VCF — it does not run WhatsHap / SHAPEIT5 / Eagle2. Run a phaser upstream and feed its VCF here.
--inputREQUIRED unless--demo.genomics_phasing.py:314raisesValueError("--input required when not using --demo"); non-existent paths raiseFileNotFoundErrorat:317.- Unphased VCFs produce empty phase-block tables. A VCF without any
|genotypes orPSfields will reportphased_fraction = 0and an emptyphase_blocks.csv— but the run does NOT fail. Always check the summary before drawing conclusions. PSis required for block grouping — without it you get ZERO blocks. WhenPSis absent,genomics_phasing.py:126falls back tostr(pos)so every variant becomes a singleton phase-set; then:157filters out blocks with< 2variants, producing zero phase blocks andphase_block_n50_bp = 0. WhatsHap output always includesPS; some other phasers do not — verify before interpreting an "unphased" report.- Multi-sample VCFs are NOT supported. Only the first sample column is parsed; multi-sample phasing comparison is out of scope.
- Demo VCF synthesises ~80% phased het variants in 5–20 blocks. 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.
- 4d ago First seen · 89 lines · 77 tokens per session scan A 1c83822184ef
genomics-phasing is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,128 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
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…
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…
braindb
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
batch-processor
Manage large document processing by splitting into batches and coordinating the full translation workflow (extraction, translation, formatting). Use when handling documents larger than 30 pages, 60 paragraphs, or 6000 words.
markdown-formatter
Format and optimize Markdown content, with special support for post-translation processing. Use when fixing Markdown syntax, adjusting layout, ensuring formatting consistency, or optimizing translated documents.