Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zongtingwei/Bioclaw_Skills_Hubnpx agentmods add skills/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoringWrote 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/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoring)<a href="https://agentmods.dev/skills/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoring"><img src="https://agentmods.dev/badge/skills/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoring/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/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoring"><img src="https://agentmods.dev/badge/skills/zongtingwei/bioclaw_skills_hub/esm2-sequence-scoring.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00111 | $0.01583 |
| Opus 5 | $0.00056 | $0.00792 |
| Sonnet 5 | $0.00022 | $0.00317 |
| Haiku 4.5 | $0.00011 | $0.00158 |
Grade A, and why
esm2-sequence-scoring 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ESM2 Protein Language Model
Plain-language role: Use ESM when you want sequence-level scoring or embeddings rather than 3D structure prediction.
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.8+ | 3.10 |
| PyTorch | 1.10+ | 2.0+ |
| CUDA | 11.0+ | 11.7+ |
| GPU VRAM | 8GB | 24GB (A10G) |
| RAM | 16GB | 32GB |
How to run
First time? See Installation Guide to set up Modal and biomodals.
Option 1: Modal
cd biomodals
modal run modal_esm2_predict_masked.py \
--input-faa sequences.fasta \
--out-dir embeddings/
GPU: A10G (24GB) | Timeout: 300s default
Option 2: Python API (recommended)
import torch
import esm2-sequence-scoring
# Load model
model, alphabet = esm2-sequence-scoring.pretrained.esm2_t33_650M_UR50D()
batch_converter = alphabet.get_batch_converter()
model = model.eval().cuda()
# Process sequences
data = [("seq1", "MKTAYIAKQRQISFVK...")]
batch_labels, batch_strs, batch_tokens = batch_converter(data)
with torch.no_grad():
results = model(batch_tokens.cuda(), repr_layers=[33])
# Get embeddings
embeddings = results["representations"][33]
Key parameters
ESM2 Models
| Model | Parameters | Speed | Quality |
|---|---|---|---|
| esm2_t6_8M | 8M | Fastest | Fast screening |
| esm2_t12_35M | 35M | Fast | Good |
| esm2_t33_650M | 650M | Medium | Better |
| esm2_t36_3B | 3B | Slow | Best |
Output format
embeddings/
├── embeddings.npy # (N, 1280) array
├── pll_scores.csv # PLL for each sequence
└── metadata.json # Sequence info
Sample output
Successful run
$ modal run modal_esm2_predict_masked.py --input-faa designs.fasta
[INFO] Loading ESM2-650M model...
[INFO] Processing 100 sequences...
[INFO] Computing pseudo-log-likelihood...
embeddings/pll_scores.csv:
sequence_id,pll,pll_normalized,length
design_0,-0.82,0.15,78
design_1,-0.95,0.08,85
design_2,-1.23,-0.12,72
...
Summary:
Mean PLL: -0.91
Sequences with PLL > 0: 42/100 (42%)
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.
- 12d ago First seen · 200 lines · 111 tokens per session scan A ed422e32c4aa
esm2-sequence-scoring is a skill published in the GitHub repository zongtingwei/Bioclaw_Skills_Hub (26 stars, last pushed 5mo ago), licensed MIT. It adds 111 tokens to every session and 1,583 once invoked, about $0.0006 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
esm2-sequence-scoring
ESM2 protein language model for sequence scoring, embeddings, and plausibility checks. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing…
esm
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships.…
esm
ESM protein language models for embeddings, sequence scoring, structure prediction, and binder design. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) or mutation-effect scores, (2) Getting protein embeddings for clustering or filtering, (3) Predicting complex structures with ESMFold2, (4) Designing…
esm
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships.…
jupyter-live-kernel
Iterative Python via live Jupyter kernel (hamelnb).
ilya-sutskever-perspective
A thinking guide based on Ilya Sutskever’s public conversations, research papers, testimony, and recommended sources. It applies that material to AI research direction, technical reasoning, and safety questions.