A toolkit for analysing single-cell RNA sequencing data, which measures gene activity in individual cells. It works with H5AD files and supports quality checks, cell grouping, gene comparisons, and visual maps such as UMAP.

Filtering and normalising single-cell data, finding cell clusters, comparing gene activity between clusters or conditions, and testing which biological pathways the changed genes may involve.

It provides a structured way to turn large single-cell datasets into groups of similar cells and identify genes that differ between groups.

How omar-A-hassan/medsci-agent configures OpenCode

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/skills/scanpy/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/omar-A-hassan/medsci-agent

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/scanpy/github.svg)](https://agentmods.dev/skills/omar-a-hassan/medsci-agent/scanpy)

Your own site

<a href="https://agentmods.dev/skills/omar-a-hassan/medsci-agent/scanpy"><img src="https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/scanpy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/omar-a-hassan/medsci-agent/scanpy"><img src="https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/scanpy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 383 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00383
Opus 5.5	$0.00012	$0.00153
Sonnet 5.5	$0.00006	$0.00077
Haiku 4.5	$0.00003	$0.00038

Measured 2mo ago against content hash 6211f34441a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scanpy 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 2mo 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/skills/scanpy/SKILL.md · 37 lines

What it actually says

Scanpy — Single-Cell Analysis

When to Use

Loading and exploring .h5ad (AnnData) files
QC, filtering, normalization of single-cell data
Cell clustering (Leiden/Louvain)
Differential expression between clusters or conditions
UMAP/t-SNE dimensionality reduction

Standard Pipeline

1. Read data    → read_h5ad(path)
2. QC filtering → preprocess_omics(path, min_genes=200, min_cells=3)
3. Normalize    → (included in preprocess step)
4. HVG select   → (included in preprocess step, n_top_genes=2000)
5. Cluster      → cluster_cells(path, method="leiden", resolution=1.0)
6. DE analysis  → differential_expression(path, groupby="leiden")
7. Enrichment   → gene_set_enrichment(genes=[...top DE genes])

Key Parameters

resolution: Controls granularity of clustering. 0.4-0.8 for broad clusters, 1.0-2.0 for fine-grained
min_genes: Cells with fewer genes are likely empty droplets (default 200)
min_cells: Genes in fewer cells are likely noise (default 3)
n_top_genes: Highly variable genes for downstream analysis (default 2000)

Interpreting Results

Cluster sizes should be relatively balanced — very small clusters may be doublets
DE genes with |log2FC| > 1 and padj < 0.05 are considered significant
Check for batch effects before biological interpretation

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.

2mo ago First seen · 37 lines · 29 tokens per session scan A 6211f34441a7

Subscribe to this mod's changes

scanpy is a skill published in the GitHub repository omar-A-hassan/medsci-agent (17 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 383 once invoked, about $0.0001 per session on Opus 5.5. 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.

Scientific agents mcp medgemma ollama opencode txgemma

scanpy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
scanpyomar-A-hassan/medsci-agent	Skill	17	2mo ago	MIT	A	29	OpenCode
build-expression-treejimmc414/claude-code-plugin-marketplace	Skill	4	yesterday	MIT	A	24	Claude Code
find-convex-hulljimmc414/claude-code-plugin-marketplace	Skill	4	yesterday	MIT	A	31	Claude Code
dfam-checkearthtojake/text-to-cad	Skill	26k	yesterday	MIT	A	117	Claude Code, Codex
peer-reviewxintaofei/codeg	Skill	4.2k	6d ago	Apache-2.0	A	71	Claude Code
scientific-critical-thinkingxintaofei/codeg	Skill	4.2k	6d ago	Apache-2.0	A	63	Claude Code
tooluniverse-phylogeneticsmims-harvard/ToolUniverse	Skill	1.8k	yesterday	Apache-2.0	A	155	Claude Code

medsci-agent: Skill for OpenCode