agentmods.dev

deconvolve-immune

deconvolve-immune is a command for Claude Code from zamushwani/biomedical-ai-skills. It costs 0 tokens per session (302 once invoked), scanned A, original, MIT.

A command for estimating the mixture of immune cell types in bulk RNA sequencing data, where measurements combine signals from many cells.

In plain words
What is it for?
Use it with methods such as quanTIseq, CIBERSORT, xCell, or MCP-counter to produce cell fractions or scores and compare results across methods.
Why use it?
It helps estimate tumour immune infiltration while avoiding errors caused by the wrong data scale, incomparable score types, or differences in tumour purity.

Command for Claude Code

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

not rated 1repo 1mo ago A scan 0 tokens original MIT

Good fit Use it with methods such as quanTIseq, CIBERSORT, xCell, or MCP-counter to produce cell fractions or scores and compare results across methods.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/zamushwani/biomedical-ai-skills/deconvolve-immune
View source ↗ zamushwani/biomedical-ai-skills
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 deconvolve-immune

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/zamushwani/biomedical-ai-skills/deconvolve-immune"><img src="https://agentmods.dev/badge/commands/zamushwani/biomedical-ai-skills/deconvolve-immune.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 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 $0.00000 $0.00302
Opus 5.5 $0.00000 $0.00121
Sonnet 5.5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured 2mo ago against content hash f3d6067f89e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deconvolve-immune 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.

.claude/commands/deconvolve-immune.md · 19 lines

What it actually says

Estimate immune composition for $0 using method $1 (default: quanTIseq).

Follow the immune-deconvolution skill. The parts that are usually got wrong:

  1. Method dictates the input scale. quanTIseq and CIBERSORT expect TPM; some methods want un-logged values. Feeding log-TPM where TPM is expected produces plausible-looking, wrong fractions.
  2. Know what the output means. quanTIseq and EPIC give fractions comparable across cell types within a sample; xCell and MCP-counter give scores comparable across samples within a cell type. Comparing an xCell score between two cell types is meaningless.
  3. Correct for tumour purity where it matters — immune fractions are diluted by tumour content, so a purity difference between groups masquerades as an immune difference.
  4. Run more than one method and report where they disagree. Agreement across methods is the only cheap validation available.

Report: the fraction/score matrix, which method and input scale were used, and a cross-method comparison for the key cell types.

If $0 is empty, ask for the expression matrix.

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. 2mo ago First seen · 19 lines · 0 tokens per session scan A f3d6067f89e9

Subscribe to this mod's changes

deconvolve-immune is a command published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 302 tokens. 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.

DESeq2Scientificai-agentai-skillsbioinformaticscancer-genomicscancer-research
Related

deconvolve-immune compared with commands from other repositories

deconvolve-immune next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deconvolve-immunezamushwani/biomedical-ai-skillsCommand11mo agoMITA0Claude Code
readaipoch/medical-research-skillsCommand2.0k1mo agoMITA0Claude Code
feedaipoch/medical-research-skillsCommand2.0k1mo agoMITA0Claude Code
annotateHERRY423/CellTypePilotCommand62mo agoMITA16Claude Code
criticHERRY423/CellTypePilotCommand62mo agoMITA14Claude Code
ctp-inspectHERRY423/CellTypePilotCommand62mo agoMITA16Claude Code
faostat-country-profileberba-q/faostat-skillsCommand106mo agoMITA10Claude Code