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 agentmods add skills/aipoch/open-science/evo2npx skills add aipoch/open-science --skill evo2git 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/evo2)<a href="https://agentmods.dev/skills/aipoch/open-science/evo2"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/evo2.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00083 | $0.01484 |
| Opus 5 | $0.00042 | $0.00742 |
| Sonnet 5 | $0.00017 | $0.00297 |
| Haiku 4.5 | $0.00008 | $0.00148 |
Grade A, and why
evo2 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 4d 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:
- evo2 — 98% identical, 54 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evo 2 — DNA Language Model
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.11 | 3.12 (<3.13) |
| CUDA | 12.1+ | 12.4+ |
| GPU VRAM | 24 GB (7B bf16) | 80 GB (40B) |
| RAM | 32 GB | 128 GB |
How to run
Installation
pip install evo2
# Weights pulled from Hugging Face on first model load.
Loading and scoring
from evo2 import Evo2
model = Evo2("evo2_7b") # or "evo2_40b" — see model table
seqs = ["ATCG" * 50, "GGGCTTAA" * 25]
ll = model.score_sequences(seqs) # → list[float], mean per-token log-likelihood
print(ll)
Generation
out = model.generate(
prompt_seqs=["ATGAAAGCT"],
n_tokens=256,
temperature=0.7,
)
print(out.sequences[0])
Models
| Name | Params | Context | VRAM (bf16) | Notes |
|---|---|---|---|---|
evo2_7b |
7 B | 1 M nt | ~22 GB | Default; fits on a single 24 GB+ GPU |
evo2_40b |
40 B | 1 M nt | ~78 GB | H100 80 GB or multi-GPU |
evo2_1b_base |
1 B | 8 K nt | ~6 GB | FP8 path requires sm_89+ (H100) |
Output format
score_sequences returns a list[float] (or np.ndarray) of mean log-likelihoods,
one per input sequence. More negative ⇒ less likely under the model. For variant
effect, compute Δll = ll_alt - ll_ref over a fixed window.
generate returns a GenerationOutput with .sequences (list[str]), .logits
(list[Tensor]), and .logprobs_mean (list[float]) — always populated, no flag required.
Decision tree
Need a DNA model?
│
├─ Per-base/per-sequence likelihood, generation → Evo 2 ✓
├─ Predict experimental tracks (expression, accessibility) → borzoi
└─ Protein, not DNA → fair-esm2 / esmfold2
Remote compute
7B/40B inference is GPU-bound (≥24 GB / 80 GB VRAM). Read
compute_details({provider, mode:'read'}) for an environment with evo2 +
flash-attn and a pre-cached HF weight mount, then submit:
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.
- 4d ago First seen · 152 lines · 83 tokens per session scan A 95f2a4439715
evo2 is a skill published in the GitHub repository aipoch/open-science (3,497 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,484 once invoked, about $0.0004 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.
Other skills, from other repositories
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
source-verify
医学信源快速或完整核验。普通教育性医学问答用单一权威正文快速核验；最新版本、精确推荐、高风险药品、医保监管或跨版本请求升级为完整核验。只整理学习依据，不生成诊疗、处方、急诊处置、医保报销结论或HIS执行建议。.
clinical-q-and-a
快速回答普通教育性医学问题与常见误区。默认用一份国内现行权威指南/共识完成轻量核验并立即作答；不用于个体诊疗、处方剂量、精确推荐定位、药品高风险事实、医保监管或跨版本比较。.
guideline-section-expansion
用户反馈里最常见的两句话是「指南查到了但展不开」和「能不能把指南总结成流程」。本 skill 处理这两件事，并把它们严格限定为学习产物。.
guideline-learning-diagnosis
当用户要求评估自己对某份指南的掌握情况、制定指南学习/备考计划、梳理薄弱章节、 做教育性小测，或学习指南中的诊断标准、鉴别框架和流程关系时使用。 本技能只做学习诊断与诊断标准教学，不对具体患者作疾病诊断、治疗、处方、剂量、 急诊处置或医保报销判断。.
medical-source-failover
Route retrieval of Chinese medical guidelines, consensus statements, regulatory documents, drug information, safety notices, standards, and public-health materials through authoritative originals and verified fallback copies. Use when a canonical medical source is blocked, slow, unavailable, moved, paywalled, or…