scgpt

scgpt is a skill for Claude Code, Codex from companion-inc/feynman. It costs 39 tokens per session (168 once invoked), scanned A, original, MIT.

A guide for scGPT-style analysis of single-cell biology data. Single-cell analysis studies measurements from individual cells, while scGPT is a foundation-model workflow for tasks such as cell labeling and gene analysis.

In plain words
What is it for?
Use it for single-cell embeddings, cell annotation, perturbation prediction, batch transfer, and gene-program analysis.
Why use it?
It helps keep the data source, preprocessing, model version, labels, and biological evidence documented so results can be checked and compared.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for single-cell embeddings, cell annotation, perturbation prediction, batch transfer, and gene-program analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/companion-inc/feynman/scgpt
About the project

Feynman is an open-source AI research agent that helps users investigate topics with language models. It supports local model providers and hosted model authentication through its setup process. The catalogue contains skills, agents, and instructions that extend Feynman’s workflows.

companion-inc/feynman · 8,870 stars · on GitHub · feynman.is

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.

Any agent
npx skills add companion-inc/feynman --skill scgpt
Clone the repo
git clone --depth 1 https://github.com/companion-inc/feynman

Made for: Claude Code, Codex.

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 scgpt

README.md
[![agentmods](https://agentmods.dev/badge/skills/companion-inc/feynman/scgpt/github.svg)](https://agentmods.dev/skills/companion-inc/feynman/scgpt)
Your own site
<a href="https://agentmods.dev/skills/companion-inc/feynman/scgpt"><img src="https://agentmods.dev/badge/skills/companion-inc/feynman/scgpt/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 scgpt

Your own site · 80×15
<a href="https://agentmods.dev/skills/companion-inc/feynman/scgpt"><img src="https://agentmods.dev/badge/skills/companion-inc/feynman/scgpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 168 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00168
Opus 5 $0.00019 $0.00084
Sonnet 5 $0.00008 $0.00034
Haiku 4.5 $0.00004 $0.00017

Measured 9d ago against content hash 826a7af3dd0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scgpt 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 9d 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.

skills/scgpt/SKILL.md · 19 lines

What it actually says

scGPT

Use this skill for single-cell foundation model analysis.

Workflow:

  1. Record dataset source, organism, modality, preprocessing, gene identifiers, cell labels, and perturbation design.
  2. Verify model/checkpoint/package availability before running.
  3. Save AnnData or matrix manifests, preprocessing code, model version, embeddings, predictions, plots, and logs.
  4. Compare labels or predictions against source metadata, marker genes, perturbation controls, and literature.
  5. Preserve batch, donor, disease, and assay provenance in every summary table.

Do not present cell-state labels without marker or metadata support.

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. 9d ago First seen · 19 lines · 39 tokens per session scan A 826a7af3dd0f

Subscribe to this mod's changes

scgpt is a skill published in the GitHub repository companion-inc/feynman (8,870 stars, last pushed 13d ago), licensed MIT. It adds 39 tokens to every session and 168 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 2026-08-30.

Related

Other skills, from other repositories

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…

K-Dense-AI/scientific-agent-skills · 66 tokens

torchdrug

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

K-Dense-AI/scientific-agent-skills · 61 tokens

deepspot-m

Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…

K-Dense-AI/scientific-agent-skills · 80 tokens

pyhealth

Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…

K-Dense-AI/scientific-agent-skills · 216 tokens

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

maziyarpanahi/openmed · 64 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens