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 PKU-YuanGroup/OpenAI4S --skill bio-comparative-genomics-hgt-detectiongit clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4SWrote 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/pku-yuangroup/openai4s/bio-comparative-genomics-hgt-detection)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-comparative-genomics-hgt-detection"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-comparative-genomics-hgt-detection/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/pku-yuangroup/openai4s/bio-comparative-genomics-hgt-detection"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-comparative-genomics-hgt-detection.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00189 | $0.08946 |
| Opus 5 | $0.00095 | $0.04473 |
| Sonnet 5 | $0.00038 | $0.01789 |
| Haiku 4.5 | $0.00019 | $0.00895 |
Grade A, and why
bio-comparative-genomics-hgt-detection scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([ This is a copy
95% identical to bio-comparative-genomics-hgt-detection — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: HGTector 2.0b3+, AvP 1.0.4+, HGTphyloDetect 1.0+, ALE 1.0+ (ssolo/ALE github), GeneRax 2.1.3+, AleRax 1.2.0+ (Morel 2024), RANGER-DTL 2.0+, IslandViewer 4 (web), mobileOG-db 1.0+, MetaCHIP 1.10+, IQ-TREE 2.3.6+, BioPython 1.84+, DIAMOND 2.1.10+. Open Tree of Life and NCBI Taxonomy reference databases updated 2024-Q3 minimum for HGTector/AvP.
Before using code patterns, verify installed versions match. If versions differ:
- Python:
pip show hgtectorthenhgtector search --help - CLI:
ALEml_undated --help,generax --help,alerax --help - DB:
hgtector database --checkfor taxonomy version
If code throws Taxonomy ID not found, database version mismatch, or KeyError on NCBI taxids, refresh the local taxonomy dump (NCBI updates monthly). ALE/GeneRax expect newick gene trees with bootstraps; AleRax expects gene-tree distributions (uniform bootstrap samples or UFBoot trees).
Horizontal Gene Transfer Detection
"Are these genes horizontally acquired, and from where?" -> HGT signal lives in three orthogonal signal classes: composition (recent transfers carry donor codon usage; erodes by Lawrence-Ochman 1998 amelioration in ~50-200 Myr), phylogeny (gene tree nests within distant clade), and phyletic distribution (patchy taxonomic presence). No single class proves HGT; claims require concordance across at least two classes plus mandatory exclusion of contamination and differential gene loss (DGL). The most consequential failure mode in eukaryotic HGT detection is contamination passing all three classes silently (Boothby 2015 tardigrade "17% HGT" refuted by Koutsovoulos 2016; Crisp 2015 human "145 HGTs" refuted by Salzberg 2017 GB 18:85).
- Python:
hgtector search->hgtector analyzefor BLAST-distribution screen - Python:
AvP(Koutsovoulos 2022 PLoS Comp Biol 18:e1010686) for eukaryotic phylogenetic HGT with automated tree workflow - CLI:
ALEml_undated(Szöllősi 2013 Syst Biol 62:901),generax(Morel 2020 MBE 37:2763),alerax(Morel 2024 Bioinformatics 40:btae162) for prokaryote DTL reconciliation - Web: IslandViewer 4 (Bertelli 2017 NAR 45:W30) for bacterial genomic islands
- CLI:
metachip(Song 2019 Microbiome 7:36) for metagenomic HGT inference
What ships with it
2 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 · 419 lines · 189 tokens per session scan A 06931f0cfbb6
bio-comparative-genomics-hgt-detection is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (407 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 8,946 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 95% identical to bio-comparative-genomics-hgt-detection, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
boltz-structure-prediction
Boltz-1 / Boltz-2 structure prediction for proteins, complexes, and ligand-aware validation. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.