structure-prediction-boltz-2

structure-prediction-boltz-2 is a skill for Claude Code, Codex from PharMolix/OpenBioMed. It costs 78 tokens per session (1,670 once invoked), scanned A, original, MIT.

A tool for predicting the three-dimensional structure of proteins and other biomolecules, including protein complexes and protein–molecule combinations. It uses the Boltz-2 model and can run on a local GPU.

In plain words
What is it for?
Use it to predict protein complex structures, validate designed binders, predict protein–ligand complexes, and produce predicted structures in PDB format.
Why use it?
It helps estimate how proteins may fit together or interact with a small molecule before laboratory testing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to predict protein complex structures, validate designed binders, predict protein–ligand complexes, and produce predicted structures in PDB format.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pharmolix/openbiomed/structure-prediction-boltz-2
About the project

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.

PharMolix/OpenBioMed · 1,106 stars · on GitHub

Install

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.

Any agent
npx skills add PharMolix/OpenBioMed --skill structure-prediction-boltz-2
Clone the repo
git clone --depth 1 https://github.com/PharMolix/OpenBioMed

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for structure-prediction-boltz-2

README.md
[![agentmods](https://agentmods.dev/badge/skills/pharmolix/openbiomed/structure-prediction-boltz-2/github.svg)](https://agentmods.dev/skills/pharmolix/openbiomed/structure-prediction-boltz-2)
Your own site
<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.

agentmods 80×15 button for structure-prediction-boltz-2

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash bb24fa34c656, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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)
skills/structure-prediction-boltz-2/SKILL.md · 222 lines

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)

Read the full file on GitHub · 222 lines

Changes

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.

  1. 11d ago First seen · 222 lines · 78 tokens per session scan A bb24fa34c656

Subscribe to this mod's changes

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.

Related

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…

adaptyvbio/protein-design-skills · 121 tokens

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…

adaptyvbio/protein-design-skills · 104 tokens

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.…

adaptyvbio/protein-design-skills · 107 tokens

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…

adaptyvbio/protein-design-skills · 100 tokens

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…

adaptyvbio/protein-design-skills · 84 tokens

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…

FreedomIntelligence/OpenClaw-Medical-Skills · 100 tokens