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-copy-number-germline-cnv-interpretationgit 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-copy-number-germline-cnv-interpretation)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-copy-number-germline-cnv-interpretation"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-copy-number-germline-cnv-interpretation/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-copy-number-germline-cnv-interpretation"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-copy-number-germline-cnv-interpretation.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 | $0.00154 | $0.02881 |
| Opus 5 | $0.00077 | $0.01440 |
| Sonnet 5 | $0.00031 | $0.00576 |
| Haiku 4.5 | $0.00015 | $0.00288 |
Grade A, and why
bio-copy-number-germline-cnv-interpretation 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.
This is a copy
91% identical to bio-copy-number-germline-cnv-interpretation — 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: ClassifyCNV 1.1+, AnnotSV 3.4+, Python 3.10+ with pandas 2.2+; bedtools 2.31+.
Before using code patterns, verify installed versions match. If versions differ:
- CLI:
python ClassifyCNV.py --help,AnnotSV --version - Update the bundled ClinGen/dosage databases — ClassifyCNV ships an
update_clingen.sh; dosage curation changes, and a stale database silently mis-scores.
This skill is for constitutional/germline CNVs only. Somatic tumor CNVs use a different framework (AMP/ASCO/CAP and OncoKB tiers) — do not apply ACMG/ClinGen constitutional scoring to a tumor.
Germline CNV Interpretation
"Is this constitutional CNV pathogenic" -> Apply the 2019 ACMG/ClinGen technical standards: a semiquantitative, points-based rubric that sums evidence into one of five clinical categories. There are two separate rubrics — one for copy-number loss, one for copy-number gain — because the evidence for deletion and duplication pathogenicity is different. The total score maps to a five-tier classification.
- CLI:
ClassifyCNV(automates the observed-evidence sections),AnnotSV(ACMG-aligned rank) - Manual: case-specific evidence (de novo status, segregation, prior literature) is scored by the interpreter, not the tool
The Points Framework
| Total score | Classification |
|---|---|
| >= 0.99 | Pathogenic |
| 0.90 to 0.98 | Likely pathogenic |
| -0.89 to 0.89 | Variant of uncertain significance (VUS) |
| -0.90 to -0.98 | Likely benign |
| <= -0.99 | Benign |
Evidence is grouped into sections (the loss and gain rubrics each have five). For copy-number loss: Section 1 — does the CNV contain protein-coding or functionally important elements; Section 2 — overlap with established haploinsufficient genes/regions (strong positive) or established benign regions (strong negative); Section 3 — number of protein-coding genes; Section 4 — detailed case/literature evidence (case-control, prior probands, phenotype specificity); Section 5 — inheritance (de novo with confirmed parentage is strong positive; inherited from an unaffected parent is negative). The gain rubric is structured the same way but keyed to triplosensitivity and the distinct evidence base for duplications.
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 · 199 lines · 154 tokens per session scan A a2e42f69b30a
bio-copy-number-germline-cnv-interpretation is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (407 stars, last pushed yesterday), licensed MIT. It adds 154 tokens to every session and 2,881 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to bio-copy-number-germline-cnv-interpretation, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
license-and-legal
Choose and apply an open-source license, and handle contribution and compliance mechanics. Use for picking between MIT/Apache-2.0/GPL/MPL/AGPL/BSL, adding SPDX headers, relicensing an existing project, setting up DCO or a CLA, vendoring third-party code, checking dependency license compatibility, or questions about…
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…
fda
Query openFDA via VenusFactory for drugs, devices, adverse events, recalls, and regulatory submissions (510k, PMA). Use when the user needs FDA pharmacovigilance, labeling, NDC/UNII, or openFDA analytics. Do NOT use for ChEMBL bioactivity (chembldatabase) or general biomedical literature (pubmed).
biomaterials-engineer
A world-class biomaterials engineer specializing in medical-grade material design, scaffold fabrication, biocompatibility evaluation, and regulatory compliance (ISO 10993, FDA 21 CFR Part 870). Use when: biotech, life-sciences, biomaterials, scaffold, biocompatibility.
regulatory-affairs-specialist
Elite regulatory affairs specialist specializing in drug and device registration, FDA/EMA/PMDA submissions, compliance strategy, and lifecycle management. Navigates complex regulatory pathways to accelerate market access while ensuring full compliance with global regulations.