boltz

boltz is a skill for Claude Code, Codex from adaptyvbio/protein-design-skills. It costs 104 tokens per session (1,512 once invoked), scanned A, original, MIT.

A biomolecular structure-prediction skill using Boltz-1 or Boltz-2 to estimate the three-dimensional shape of proteins, protein groups, or protein–molecule combinations.

In plain words
What is it for?
Use it to predict protein complexes, assess designed protein binders, or model protein–ligand complexes from sequence or structure inputs.
Why use it?
It helps researchers study possible molecular structures when an experimentally determined structure is not available.

Skill for Claude CodeCodex

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **First time?** See [Getting started](../../docs/getting-started.md) to set up Modal and biomodals..

Good fit Use it to predict protein complexes, assess designed protein binders, or model protein–ligand complexes from sequence or structure inputs.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills
agentmods
npx agentmods add skills/adaptyvbio/protein-design-skills/boltz

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 boltz

README.md
[![agentmods](https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/boltz/github.svg)](https://agentmods.dev/skills/adaptyvbio/protein-design-skills/boltz)
Your own site
<a href="https://agentmods.dev/skills/adaptyvbio/protein-design-skills/boltz"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/boltz/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 boltz

Your own site · 80×15
<a href="https://agentmods.dev/skills/adaptyvbio/protein-design-skills/boltz"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/boltz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,512 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00104 $0.01512
Opus 5 $0.00052 $0.00756
Sonnet 5 $0.00021 $0.00302
Haiku 4.5 $0.00010 $0.00151

Measured 11d ago against content hash 4cbaac8b6ea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

boltz 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 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.

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.

skills/boltz/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boltz Structure Prediction

Prerequisites

Requirement Minimum Recommended
Python 3.10+ 3.11
CUDA 12.0+ 12.1+
GPU VRAM 24GB 48GB (L40S)
RAM 32GB 64GB

How to run

First time? See Getting started to set up Modal and biomodals.

Option 1: Modal

cd biomodals
modal run modal_boltz.py \
  --input-faa complex.fasta \
  --out-dir predictions/

GPU: L40S (48GB) | Timeout: 1800s default

Option 2: Local installation

pip install boltz

boltz predict \
  --fasta complex.fasta \
  --output predictions/

Key parameters

Parameter Default Range Description
--recycling_steps 3 1-10 Recycling iterations
--sampling_steps 200 50-500 Diffusion steps
--use_msa_server true bool Use MSA server

FASTA Format

>protein_A
MKTAYIAKQRQISFVK...
>protein_B
MVLSPADKTNVKAAWG...

Output format

predictions/
├── model_0.cif       # Best model (CIF format)
├── confidence.json   # pLDDT, pTM, ipTM
└── pae.npy          # PAE matrix

Note: Boltz outputs CIF format. Convert to PDB if needed:

from Bio.PDB import MMCIFParser, PDBIO
parser = MMCIFParser()
structure = parser.get_structure("model", "model_0.cif")
io = PDBIO()
io.set_structure(structure)
io.save("model_0.pdb")

Comparison

Feature Boltz-1 Boltz-2 AF2-Multimer
MSA-free mode Yes Yes No
Diffusion Yes Yes No
Speed Fast Faster Slower
Open source Yes Yes Yes

Sample output

Successful run

$ boltz predict --fasta complex.fasta --output predictions/
[INFO] Loading Boltz-1 weights...
[INFO] Predicting structure...
[INFO] Saved model to predictions/model_0.cif

predictions/confidence.json:
{
  "ptm": 0.78,
  "iptm": 0.65,
  "plddt": 0.81
}

What good output looks like:

  • pTM: > 0.7 (confident global structure)
  • ipTM: > 0.5 (confident interface)
  • pLDDT: > 0.7 (confident per-residue)
  • CIF file: ~100-500 KB for typical complex

Read the full file on GitHub · 201 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 · 201 lines · 104 tokens per session scan A 4cbaac8b6ea6

Subscribe to this mod's changes

boltz is a skill published in the GitHub repository adaptyvbio/protein-design-skills (158 stars, last pushed 3mo ago), licensed MIT. It adds 104 tokens to every session and 1,512 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

boltz-structure-prediction

Boltz-1 / Boltz-2 structure prediction for proteins, complexes, and ligand-aware validation. 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…

zongtingwei/Bioclaw_Skills_Hub · 121 tokens

boltz-structure-prediction

Boltz-1 / Boltz-2 structure prediction for proteins, complexes, and ligand-aware validation. 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…

BioTender-max/awesome-bio-agent-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…

BioTender-max/awesome-bio-agent-skills · 104 tokens

protenix

Structure prediction using Protenix, ByteDance's open-source PyTorch reproduction of AlphaFold 3. Use this skill when: (1) Predicting protein/DNA/RNA/ligand/ion complex structures, (2) Need AF3-level accuracy with open-source code, (3) MSA-free fast prediction (--no-use-msa), (4) Multi-seed ensemble predictions, (5)…

BioTender-max/ProteinClaw · 123 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…

BioTender-max/ProteinClaw · 104 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