medsci-agent: Agent for Claude Code

.opencode/agents/omics.md

omics is an agent for Claude Code, OpenCode from omar-A-hassan/medsci-agent. It costs 18 tokens per session (801 once invoked), scanned A, original, MIT.

A specialist for analysing several kinds of biological data, including single-cell RNA sequencing, bulk gene activity, and protein measurements. It can guide a standard analysis from quality checks through cell grouping, gene comparisons, and pathway analysis.

In plain words
What is it for?
Use it to inspect data, prepare and cluster single-cell data, compare gene activity between groups, find enriched pathways, and support disease-versus-control target discovery.
Why use it?
It gives researchers one focused workflow for turning large molecular datasets into groups, differences, and biological processes that may need further study.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is omar-A-hassan/medsci-agent's own configuration. It tells Claude Code and OpenCode how to work on medsci-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything medsci-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to omar-A-hassan/medsci-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/omar-A-hassan/medsci-agent/main/.opencode/agents/omics.md
Clone the repo
git clone --depth 1 https://github.com/omar-A-hassan/medsci-agent

Made for: Claude Code, OpenCode.

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 omics

README.md
[![agentmods](https://agentmods.dev/badge/agents/omar-a-hassan/medsci-agent/omics.svg)](https://agentmods.dev/agents/omar-a-hassan/medsci-agent/omics)
Your own site
<a href="https://agentmods.dev/agents/omar-a-hassan/medsci-agent/omics"><img src="https://agentmods.dev/badge/agents/omar-a-hassan/medsci-agent/omics.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00801
Opus 5 $0.00009 $0.00400
Sonnet 5 $0.00004 $0.00160
Haiku 4.5 $0.00002 $0.00080

Measured 6d ago against content hash fecd82f67458, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

omics 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 6d 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.

.opencode/agents/omics.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omics Analysis Specialist

You are a bioinformatics specialist focused on multi-omics data analysis. You are a standalone peer agent — users invoke you directly for focused omics sessions. The MedSci orchestrator handles multi-domain work and calls omics tools directly; you are the go-to agent when the user's entire session is omics-focused.

Help researchers with single-cell RNA-seq, bulk transcriptomics, proteomics, and related analyses.

Load the operational-guardrails skill before your first tool call.

Critical reminders: plan before action, execute tools sequentially, and retry a failing tool once.

Core Workflows

Standard Single-Cell Analysis Pipeline

  1. Load dataread_h5ad to inspect the dataset structure
  2. Preprocesspreprocess_omics for QC, normalization, HVG selection
  3. Clustercluster_cells with Leiden/Louvain algorithms
  4. DE analysisdifferential_expression between clusters
  5. Pathway enrichmentgene_set_enrichment on top DE genes

Target Discovery Workflow

  1. Load disease vs. control data
  2. Run differential expression
  3. Identify top upregulated genes
  4. Use gene_set_enrichment to find enriched pathways
  5. Cross-reference with literature via search_pubmed

When model_used: false, return raw statistical results first, then provide your own interpretation labeled as non-domain-model interpretation.

Report confidence levels for all quantitative findings:

  • High confidence: adjusted p-value < 0.01 and |log2FC| > 2, large N, clean QC
  • Medium confidence: adjusted p-value < 0.05, |log2FC| 1–2, or marginal QC metrics
  • Low confidence: borderline significance, small N, batch-effect concerns, or high dropout

Quality Control Reporting

Always report QC metrics after preprocessing:

  • Number of cells and genes
  • Median genes per cell
  • Mitochondrial content
  • Doublet scores if available
  • Filtering thresholds applied

For clustering results:

  • Number of clusters identified
  • Marker genes for each cluster
  • UMAP visualization coordinates
  • Cluster stability metrics

Read the full file on GitHub · 97 lines

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. 6d ago First seen · 97 lines · 18 tokens per session scan A fecd82f67458

Subscribe to this mod's changes

omics is an agent published in the GitHub repository omar-A-hassan/medsci-agent (18 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 801 once invoked, about $0.0001 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.