Open Science is a local-first, model-agnostic workbench for reproducible scientific research. Scientists use its AI agents, Python and R execution, data connectors, and traceable outputs for tasks such as literature review, analysis, simulation, and visualization across macOS, Windows, and Linux.
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.
npx skills add aipoch/open-science --skill scgptgit clone --depth 1 https://github.com/aipoch/open-scienceWrote 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.
[](https://agentmods.dev/skills/aipoch/open-science/scgpt)<a href="https://agentmods.dev/skills/aipoch/open-science/scgpt"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/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.
<a href="https://agentmods.dev/skills/aipoch/open-science/scgpt"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/scgpt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 136 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 138 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 140 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 139 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00089 | $0.01360 |
| Opus 5.5 | $0.00036 | $0.00544 |
| Sonnet 5.5 | $0.00018 | $0.00272 |
| Haiku 4.5 | $0.00009 | $0.00136 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- scgpt — 100% identical, 41 lines differ
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scGPT — Single-Cell Foundation Model
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.10+ | 3.11 |
| CUDA | 12.1+ | 12.4+ |
| GPU VRAM | 16 GB | 24 GB+ |
How to run
Loading the vocabulary and checkpoint
scGPT checkpoints are raw directories (args.json, best_model.pt,
vocab.json) — not Hugging Face hub repos. Point at the directory, not an HF
repo id.
from scgpt.tokenizer.gene_tokenizer import GeneVocab
gv = GeneVocab.from_file("/path/to/scgpt-human/vocab.json")
print(len(gv)) # 60697 for the released human checkpoint
Embedding an AnnData
import anndata as ad
from scgpt.tasks import embed_data
adata = ad.read_h5ad("dataset.h5ad") # var must contain a gene-name column
emb = embed_data(
adata,
model_dir="/path/to/scgpt-human",
gene_col="feature_name",
use_fast_transformer=False, # see Gotchas
)
# emb is an AnnData with .obsm["X_scGPT"]
Output format
embed_data returns an AnnData whose .obsm["X_scGPT"] is the per-cell
embedding (n_cells × emb_dim, 512 by default). Downstream: feed to
scanpy.pp.neighbors / scanpy.tl.umap.
Remote compute
Needs ≥24 GB VRAM and the released human checkpoint (~200 MB:
args.json, best_model.pt, vocab.json). Read
compute_details({provider, mode:'read'}) for an environment with scgpt
and a pre-cached checkpoint directory, then:
c = host.compute.create(provider)
job = c.submitJob(
intent="scGPT embed 50k cells — 1×GPU, ~5 min",
inputs=[
{"src": "dataset.h5ad", "dstFilename": "dataset.h5ad"},
{"src": "embed.py", "dstFilename": "embed.py"},
],
command="python3 embed.py",
environment=..., # env name from compute_details
outputs=["embedded.h5ad"],
timeoutSeconds=1800,
)
print(job.job_id) # cell ends here — kernel never blocks on compute
Retain the exact returned job_id. Query that saved ID with the non-blocking
host.compute.create(provider).attachJob(job_id).status() or .result() when its state or result
is relevant; do not scan Job history. A final .result() read reports whether its follow-up was suppressed
or had already been committed; otherwise the app starts the later analysis turn for an unread
final result. See the remote-compute-ssh skill for the orchestration details.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -11 lines a87b3b7f3990
- 1mo ago First seen · 148 lines · 89 tokens per session scan A c28cd78216ec
scgpt is a skill published in the GitHub repository aipoch/open-science (5,301 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 1,360 once invoked, about $0.0004 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.
Other skills, from other repositories
analysis-workflow
Organize multi-step scientific analyses into reproducible, self-contained modules. Use for workflows such as QC→PCA→DEG→GSEA that produce scripts, inputs, figures, tables, and methods. Creates a stable module layout, records exact inputs/parameters/package and database versions in each module README, keeps large data…
public-data-access
Plan, validate, and document public-bioinformatics data acquisition for GEO/GSE/GSM/GPL/GDS, SRA/ENA, TCGA/GDC, GTEx, and DepMap. Covers expression matrices, raw reads, download manifests, caches, and optional geokit SOFT/Series Matrix acquisition for R workflows.
journal-club-ppt
Instructions for turning a scientific paper PDF into a journal-club presentation or literature report. They require reconstructing the paper's scientific logic before creating the slides.
figure-style
Correctness and legibility checklist for publication figures, plus a matplotlib sidecar. Load before plotting anything and call applyfigurestyle() (role-mapped font ladder, outward ticks, frameless legends, 300-dpi saves, CJK-safe fonts). Covers data fidelity, label budgets, axis/colour/type rules, chart choice by…
research-integrity-audit
A research-integrity review of a scientific manuscript's figures and reported numbers. It looks for possible image reuse or alteration and numerical patterns that may indicate data inconsistencies.
audit-biomedical-paper-evidence
A reviewer for life-science and biomedical papers, PDFs, figures, captions, and screenshots. It examines the scientific question, experiments, evidence, causality, and limitations.