OpenBioMed is an agent platform and toolkit collection for biomedical research and drug discovery, covering areas such as molecular design, protein analysis, and single-cell data analysis. It is intended for researchers and provides the biomedical skills listed in the catalogue as workflows for Claude Code.
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 PharMolix/OpenBioMed --skill structure-prediction-boltz-2git clone --depth 1 https://github.com/PharMolix/OpenBioMedWrote 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/pharmolix/openbiomed/structure-prediction-boltz-2)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/structure-prediction-boltz-2"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/structure-prediction-boltz-2/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/pharmolix/openbiomed/structure-prediction-boltz-2"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/structure-prediction-boltz-2.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 | $0.00078 | $0.01670 |
| Opus 5 | $0.00039 | $0.00835 |
| Sonnet 5 | $0.00016 | $0.00334 |
| Haiku 4.5 | $0.00008 | $0.00167 |
Grade A, and why
structure-prediction-boltz-2 scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
process = subprocess.Popen(command, stdout=f, stderr=f, env=self.env) How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boltz-2 Structure Prediction
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.10+ | 3.10 |
| CUDA | 12.0+ | 12.2 |
| GPU VRAM | 24GB | 80GB (A800) |
| RAM | 32GB | 64GB |
How to run
Local installation
pip install boltz[cuda] -U -i
Predict protein complex structure
import os, yaml, subprocess
def predict_protein_complex_structure(sequence_1, sequence_2, project_dir):
"""
:param sequence_1: sequence of the first protein
:param sequence_2: sequence of the second protein
:param project_dir: path to the project
:return structure of the protein complex in PDB format
"""
# init project dir
os.makedirs(project_dir, exist_ok=True)
log_file = os.join(project_dir, 'log.txt')
# init input yaml file
data = {
"sequences": [
{
"protein": {
"id": "A",
"sequence": sequence_1,
"msa": "empty"
}
},
{
"protein": {
"id": "B",
"sequence": sequence_2,
"msa": "empty"
}
},
]
}
input_file = os.path.join(project_dir, "input.yaml")
with open(input_file, "w") as f:
yaml.dump(data, f)
# init output file
output_dir = os.path.join(project_dir, "boltz")
# prediction
command = [
'boltz', 'predict', input_file,
"--out_dir", output_dir,
'--use_msa_server',
'--output_format', "pdb",
"--seed", "42"
]
with open(log_file, 'a') as f:
process = subprocess.Popen(command, stdout=f, stderr=f, env=self.env)
process.communicate()
process.terminate()
try:
process.wait(timeout=5)
except subprocess.TimeoutExpired:
process.kill()
process.wait()
# extract structure
with open(os.path.join(output_dir, "boltz_results_input", "predictions", "input", "input_model_0.pdb"), 'r') as f:
pred_struc = f.read()
return pred_struc
# Predict protein complex structure for sequence_1 and sequence_2
# pred_structure is the structure prediction in PDB format
pred_structure = predict_protein_complex_structure(sequence_1, sequence_2, project_dir)
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.
- 11d ago First seen · 222 lines · 78 tokens per session scan A bb24fa34c656
structure-prediction-boltz-2 is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,670 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
boltz
Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC thresholds, use…
chai
Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2.…
alphafold
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction…
protenix
Structure prediction with Protenix, an open AlphaFold3 reproduction. Use this skill when: (1) Predicting complex structures with an AF3-class model, (2) Wanting an open alternative to AF3 alongside Boltz and Chai, (3) Validating designed binder-target complexes. For QC thresholds, use protein-qc. For ipSAE ranking…
alphafold
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction…