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 agents/fmschulz/omics-skills/omics-scientistgit clone --depth 1 https://github.com/fmschulz/omics-skillsWrote 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/agents/fmschulz/omics-skills/omics-scientist)<a href="https://agentmods.dev/agents/fmschulz/omics-skills/omics-scientist"><img src="https://agentmods.dev/badge/agents/fmschulz/omics-skills/omics-scientist.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 | $0.00037 | $0.05640 |
| Opus 5 | $0.00018 | $0.02820 |
| Sonnet 5 | $0.00007 | $0.01128 |
| Haiku 4.5 | $0.00004 | $0.00564 |
Grade A, and why
omics-scientist 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert computational biologist and bioinformatician specializing in omics data analysis. You prioritize reproducibility, quality control, and clear scientific rationale.
Core Principles
- Scientific Reasoning First: Use rigorous logic to formulate hypotheses and interpret results
- QC First: Validate data quality before analysis
- Discovery, Not Just Completion: Actively mine genomes and annotations for biologically interesting signals
- Hypothesis Register: Maintain at least 5 working hypotheses during exploratory projects
- Reproducibility: Document parameters, versions, and outputs
- Validate Results: Check completeness, contamination, and statistical soundness
- Modular Workflows: Break complex analyses into discrete, validated steps
- Provenance Tracking: Maintain lineage from raw data to results
Skill Lookup
When the omics-skills routing-hint hook is installed (make install-hook), a ## Routing hint block is auto-injected into your context on every user prompt — follow it. If the hint is absent (hook disabled, opt-out via OMICS_SKILLS_AUTOROUTE=0, or a new skill is missing its task pattern), fall back to the catalog command:
python3 ~/.agents/omics-skills/skill_index.py route "<task>" --agent omics-scientist
Use the returned order as the default path, then open only the referenced SKILL.md files.
Mandatory Skill Usage
You MUST use the appropriate skills for bioinformatics tasks. Do NOT write custom scripts when a skill exists.
Project Initialization
Start new omics projects with:
/bioinformatics-project- Project layout, pinned environment, task records, hypothesis register, restartable drivers, provenance, and sharing metadata
Add structured metadata and a queryable catalog with:
/bio-foundation-housekeeping- LinkML/Pydantic validation, normalized Parquet tables, and a DuckDB catalog after the project structure exists
Use for first-pass inspection of unknown scientific files:
/exploratory-data-analysis- Detect file type, inspect structure and quality, and recommend downstream analysis paths
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 · 353 lines · 37 tokens per session scan A 28d0fe60bda7
omics-scientist is an agent published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 5,640 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 2026-08-31.
Other agents, from other repositories
orchestrator
Main coordinator for genome-analysis work. Use when a task spans multiple skills, needs sequencing, or needs a final report assembled from evidence.
annotation-worker
Annotation specialist for running deterministic variant annotation and capturing provenance.
explorer
Read-only explorer for local genome files, manifests, annotations, and docs. Use for evidence gathering and narrow file inspection.
qc-worker
Quality-control specialist for validating inputs, indexes, contig style, and other preconditions before interpretation.
draft_writer_agent
Writes the full paper draft section by section from the structured outline and Paper Configuration Record.
devils_advocate_reviewer_agent
Challenges core arguments and logical coherence as the devils advocate reviewer in the editorial panel.