analyze-degs

analyze-degs is a command for Claude Code from zamushwani/biomedical-ai-skills. It costs 39 tokens per session (309 once invoked), scanned A, original, MIT.

A command for finding genes whose activity differs between conditions from a bulk RNA-sequencing count matrix. Differential expression analysis compares gene counts between groups, such as treated and untreated samples.

In plain words
What is it for?
Use it to identify differentially expressed genes, create a volcano plot, rank genes with shrunken effect sizes, and report adjusted statistical results.
Why use it?
It prevents common analysis errors, including using normalized values where raw counts are required, reversing the comparison direction, or treating unstable low-count effects as reliable.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to identify differentially expressed genes, create a volcano plot, rank genes with shrunken effect sizes, and report adjusted statistical results.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/zamushwani/biomedical-ai-skills/analyze-degs
Install

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.

Clone the repo
git clone --depth 1 https://github.com/zamushwani/biomedical-ai-skills

Made for: Claude Code.

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 analyze-degs

README.md
[![agentmods](https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/analyze-degs/github.svg)](https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/analyze-degs)
Your own site
<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/analyze-degs"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/analyze-degs/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.

agentmods 80×15 button for analyze-degs

Your own site · 80×15
<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/analyze-degs"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/analyze-degs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00309
Opus 5 $0.00019 $0.00154
Sonnet 5 $0.00008 $0.00062
Haiku 4.5 $0.00004 $0.00031

Measured 11d ago against content hash 8e5ff4d8af3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

analyze-degs 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 11d 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.

.claude/commands/analyze-degs.md · 20 lines

What it actually says

Run a differential expression analysis on $0 using the condition column $1.

Follow the cancer-multiomics skill. The parts that are usually got wrong:

  1. Feed DESeq2 raw integer counts. Not TPM, not FPKM, not anything normalized. DESeq2 models counts and its dispersion estimates are invalid on normalized input.
  2. Set the factor reference level explicitly with relevel(), or the sign of every log2 fold change is a coin flip.
  3. Use lfcShrink() for ranking and plotting, not the raw log2FoldChange. Low-count genes have wildly inflated effect sizes otherwise.
  4. Report adjusted p-values. padj, not pvalue, and state the threshold.
  5. Check the design matrix is full rank before fitting; a confounded batch/condition design fails in a confusing way.

Report: number of genes tested, number passing padj < 0.05, the top up- and down-regulated genes with shrunk effect sizes, and any genes dropped by independent filtering.

If $0 is empty, ask which count matrix to use before running anything.

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. 11d ago First seen · 20 lines · 0 tokens per session scan A 8e5ff4d8af3c

Subscribe to this mod's changes

analyze-degs is a command published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 309 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.