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 fair-esm2git 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/fair-esm2)<a href="https://agentmods.dev/skills/aipoch/open-science/fair-esm2"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/fair-esm2/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/fair-esm2"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/fair-esm2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01627 |
| Opus 5.5 | $0.00026 | $0.00651 |
| Sonnet 5.5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
fair-esm2 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:
- fair-esm2 — 86% identical, 70 lines differ
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fair-esm2 — ESM-2 (Meta AI)
ESM-2 code and weights are MIT (Meta AI, github.com/facebookresearch/esm).
Package disambiguation.
pip install fair-esmgives youimport esmwithesm.pretrained.*(ESM-1/2). Biohub's github.com/Biohub/esm fork (MIT) gives youfrom esm.models.esmfold2 import ESMFold2InputBuilder— see theesmfold2skill. Both share theesmnamespace but are different libraries. This skill covers fair-esm (the Meta package).
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.8+ | 3.11 |
| CUDA | 11.7+ | 12.x |
| GPU VRAM | 8 GB (8M), 16 GB (650M) | 24 GB+ (650M / 3B) |
How to run
Embeddings
import torch, esm
model, alphabet = esm.pretrained.esm2_t33_650M_UR50D()
model = model.eval().cuda()
bc = alphabet.get_batch_converter()
_, _, toks = bc([("ubq", "MQIFVKTLTGKTITLEVEPSDTIENVK")])
with torch.no_grad():
out = model(toks.cuda(), repr_layers=[33])
emb = out["representations"][33] # (1, L+2, 1280) — includes BOS/EOS
seq_emb = emb[0, 1:-1].mean(0) # per-sequence mean
Masked-LM scoring
with torch.no_grad():
out = model(toks.cuda(), repr_layers=[33])
logits = out["logits"][0, 1:-1] # (L, |vocab|)
# WT marginal log-likelihood; for mutation scoring, mask the position and
# compare logit[mut] − logit[wt].
Contact prediction
with torch.no_grad():
out = model(toks.cuda(), repr_layers=[33], return_contacts=True)
contacts = out["contacts"][0] # (L, L)
Models
| Name | Layers | Dim | Params | Use |
|---|---|---|---|---|
esm2_t6_8M_UR50D |
6 | 320 | 8 M | Fast smoke / tiny embeddings |
esm2_t33_650M_UR50D |
33 | 1280 | 650 M | Default embedding model |
esm2_t36_3B_UR50D |
36 | 2560 | 3 B | Best embeddings, 24 GB+ |
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 · +18 lines b1cc3fb1a02f
- 1mo ago Changed · -6 lines 6e0f08636285
- 1mo ago First seen · 139 lines · 66 tokens per session scan A 943aa46d306f
fair-esm2 is a skill published in the GitHub repository aipoch/open-science (5,354 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 1,627 once invoked, about $0.0003 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
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…
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.
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.
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…
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.
literature-review
Retrieve, verify, and synthesize scientific literature. Use for seminal-paper lookups, evidence summaries, method comparisons, and gap analyses. Every citation must come from a live lookup, never from memory; retractions are checked; the deliverable is argued prose with resolvable DOI links.