genomics-variant-annotation

genomics-variant-annotation is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 91 tokens per session (1,231 once invoked), scanned A, original, Apache-2.0.

A reporting tool for CSV files containing variants already annotated by tools such as VEP, snpEff, or ANNOVAR. A genetic variant is a DNA difference, and its annotation describes possible effects on genes or biological functions.

In plain words
What is it for?
Use it to count HIGH, MODERATE, LOW, and MODIFIER impacts, find common consequences, count affected genes, and produce tables and a report.
Why use it?
It summarizes existing annotation data without requiring you to run variant annotation software or parse a raw VCF file.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to count HIGH, MODERATE, LOW, and MODIFIER impacts, find common consequences, count affected genes, and produce tables and a report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tiangzlab/omicsclaw/genomics-variant-annotation
Install

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.

Any agent
npx skills add TianGzlab/OmicsClaw --skill genomics-variant-annotation
Clone the repo
git clone --depth 1 https://github.com/TianGzlab/OmicsClaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for genomics-variant-annotation

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/genomics-variant-annotation.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/genomics-variant-annotation)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/genomics-variant-annotation"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/genomics-variant-annotation.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.01231
Opus 5 $0.00046 $0.00616
Sonnet 5 $0.00018 $0.00246
Haiku 4.5 $0.00009 $0.00123

Measured 8d ago against content hash c74fb1eade16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

genomics-variant-annotation 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (variant_annotation.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/genomics/genomics-variant-annotation/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

genomics-variant-annotation

When to use

The user has a CSV containing per-variant annotations (lowercase columns chrom, pos, ref, alt, consequence, impact, gene, optionally cadd_phred) — typically the output of running VEP, snpEff, or ANNOVAR upstream and exporting the resulting VCF to CSV (e.g. via bcftools +split-vep). This skill computes per-IMPACT counts, top consequences, and the count of distinct genes affected.

The script does NOT run VEP / snpEff / ANNOVAR, and does NOT parse a raw VCF — it only reads CSV. For raw calling use genomics-variant-calling; for VCF filtering use genomics-vcf-operations.

Inputs & Outputs

Inputs

  • File types: .csv
  • Accepts artifact genomics.variant_table (csv)

Outputs

  • tables/annotated_variants.csv
  • tables/impact_distribution.csv
  • report.md
  • result.json
  • Produces artifact genomics.annotated_variants as tables/annotated_variants.csv (csv)

Flow

  1. Load CSV (--input <annotated.csv>) or generate a demo annotated CSV at output_dir/demo_annotated_variants.csv with --n-variants records (variant_annotation.py:227).
  2. Read columns directly via pd.read_csv (variant_annotation.py:356) — no VCF / VEP / snpEff parser exists in this skill.
  3. Aggregate per-IMPACT counts (variant_annotation.py:240); pick top-N consequences (:241); count distinct genes touched (:252).
  4. Write tables/annotated_variants.csv (variant_annotation.py:366) + tables/impact_distribution.csv (:377) + report.md + result.json (:383).

Gotchas

  • CSV-only — no VCF parser exists. variant_annotation.py:356 is pd.read_csv(input_path); passing a .vcf raises ValueError("Could not parse input file: ...") at variant_annotation.py:358. Convert VCFs to CSV first with bcftools +split-vep -d -f '%CHROM,%POS,%REF,%ALT,%CSQ\n' and post-process to the required column names.
  • Required CSV columns are LOWERCASE. Code reads df["impact"] (:240), df["consequence"] (:241), df["gene"] (:252), and optionally df["cadd_phred"] (:271). A CSV with IMPACT / Consequence / Gene raises KeyError.
  • --input REQUIRED unless --demo. variant_annotation.py:348 raises ValueError("--input required when not using --demo"); non-existent paths raise FileNotFoundError at :351.
  • No annotator is invoked. This skill consumes an already-annotated CSV — it does NOT run VEP / snpEff / ANNOVAR. Run an annotator upstream and convert its output to CSV.
  • CADD scoring is optional. When cadd_phred is absent the report omits the CADD section; do NOT add a placeholder NaN column or the value-counts will mis-render.
  • Demo CSV uses fixed IMPACT proportions (~10% HIGH, 30% MODERATE, 50% LOW, 10% MODIFIER). Useful for orchestrator smoke tests; not biologically meaningful.

Read the full file on GitHub · 93 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 93 lines · 91 tokens per session scan A c74fb1eade16

Subscribe to this mod's changes

genomics-variant-annotation is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,231 once invoked, about $0.0005 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.

Related

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…

genomoncology/biomcp · 70 tokens

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.

genomoncology/biomcp · 36 tokens

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…

PharMolix/OpenBioMed · 105 tokens

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.

personamanagmentlayer/pcl · 59 tokens

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…

personamanagmentlayer/pcl · 83 tokens

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.

ClawBio/ClawBio · 55 tokens