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 inflexa-ai/inflexa --skill omics-generalgit clone --depth 1 https://github.com/inflexa-ai/inflexaWrote 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/inflexa-ai/inflexa/omics-general)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/omics-general"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/omics-general/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/inflexa-ai/inflexa/omics-general"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/omics-general.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 | $0.00036 | $0.02153 |
| Opus 5 | $0.00018 | $0.01077 |
| Sonnet 5 | $0.00007 | $0.00431 |
| Haiku 4.5 | $0.00004 | $0.00215 |
Grade A, and why
omics-general 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 today.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omics General Principles
Cross-cutting guidance loaded by ALL sandbox agents.
Language Policy
Python is the default language. Use R when:
- No Python equivalent exists (e.g., minfi, ANCOM-BC2, ChAMP)
- The R implementation is significantly more mature (e.g., DESeq2 for complex contrasts)
Choose native R or rpy2 based on scope:
- Isolated R calls in a Python pipeline → use rpy2 bridge
- R-dominant pipeline (most steps are R packages) → write native R scripts
AnnData/MuData: Universal Data Containers
AnnData (.h5ad) is the universal container for ALL sample-by-feature data — not just single-cell:
| Modality | .obs (samples) | .var (features) | .X (values) |
|---|---|---|---|
| Bulk RNA-seq | samples, condition, batch | genes, ensembl_id, biotype | raw counts |
| Proteomics | samples, condition, batch | proteins, uniprot_id | intensities |
| Metabolomics | samples, condition, batch | metabolite features, mz, rt | abundances |
| Microarray | samples, condition, batch | probes/genes | normalized expression |
| Single-cell | cells, cell_type, condition | genes | counts or normalized |
| Methylation (results) | samples, condition, age | CpG sites, chr, pos | beta or M-values |
MuData (.h5mu) for multi-modal data: CITE-seq (RNA+protein), Multiome (RNA+ATAC), multi-omics integration.
AnnData Conventions
- Sample metadata →
.obscolumns (never separate CSV files) - Feature annotations →
.varcolumns - Dimensionality reductions →
.obsm(e.g.,X_pca,X_umap) - Processed layers →
.layers(e.g.,raw,normalized,log1p) - Unstructured results →
.uns(DE results, method parameters) - Save as
.h5ad/.h5mu— never.rdsor.pkl
Converting from R Objects
When R produces objects (DESeqDataSet, phyloseq, SummarizedExperiment):
- Extract the data matrix, sample metadata, and feature metadata via rpy2
- Construct AnnData in Python from the extracted components
- Save as .h5ad for downstream steps
What ships with it
1 file 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.
- today First seen · 145 lines · 36 tokens per session scan A 4f0649b6cb3b
omics-general is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 2,153 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
python-dependency-version-resolution
Use when when setting up a new conda environment for a Python-based bioinformatics pipeline and you need to confirm that all declared dependencies (e.g., pysam >=0.15.4, bx-python >=0.8.8, numpy >=1.18.1, scipy >=1.4.
python-environment-management
Use when you are preparing to run Hi-C data normalization or read alignment filtering steps that depend on Python modules (iced, pysam, numpy, scipy) and you need to ensure consistent module versions across multiple runs or compute nodes.
python-pandas-data-manipulation
Use when you have precomputed expected contact frequency tables (TSV format with columns like distbp, contactfrequency, nvalid) and need to apply log-binning and smoothing to group distance values into log-spaced bins, aggregate statistics within each bin, and export a cleaned, annotated output.
biosymphony-structure-factory
Use when planning structural biology campaigns, binder-design triage, model comparison, structure mapping, RunPod or cloud GPU stage contracts, or Symphony or Linear task packs for long-running biological agent work.
binder-lane-round
Plan and run study-shaped protein-binder rounds with interchangeable toolchains, execution profiles, license gates, output checks, and result boundaries.
python-package-api-interface-design
Use when you are building or refactoring a scientific Python library and need to decide how to organize and expose utility functions (e.g., adaptive coarse-graining, filtering, analysis routines) so that end users can import and call them reliably.