boltz

boltz is a skill for Claude Code, Codex from UnicomAI/wanwu. It costs 88 tokens per session (1,475 once invoked), scanned A, a copy of boltz, Apache-2.0.

An open-weights model and command-line tool for predicting the three-dimensional structure of complexes containing proteins, DNA, RNA, and small molecules. It accepts a YAML description and returns mmCIF structure files with confidence scores, plus optional ligand-affinity predictions.

In plain words
What is it for?
Predicting protein, nucleic-acid, and small-molecule complexes; validating designed binders; and estimating ligand affinity when the optional affinity head is used.
Why use it?
Testing whether a designed binder may fit a target requires a predicted complex structure. This helps evaluate protein binders, co-fold biomolecules with ligands, and inspect confidence in the predicted arrangement.

Skill for Claude CodeCodex

About the project

Wanwu is an enterprise platform for building AI agents, workflows, retrieval-augmented applications, and managing models in multi-tenant environments. It is designed for developers and enterprise teams delivering AI applications and integrations. The catalogue entries provide skills and agents for using the platform.

UnicomAI/wanwu · 2,456 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.

agentmods
npx agentmods add skills/unicomai/wanwu/boltz
Any agent
npx skills add UnicomAI/wanwu --skill boltz
Clone the repo
git clone --depth 1 https://github.com/UnicomAI/wanwu

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/unicomai/wanwu/boltz.svg)](https://agentmods.dev/skills/unicomai/wanwu/boltz)
Your own site
<a href="https://agentmods.dev/skills/unicomai/wanwu/boltz"><img src="https://agentmods.dev/badge/skills/unicomai/wanwu/boltz.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00088 $0.01475
Opus 5 $0.00044 $0.00737
Sonnet 5 $0.00018 $0.00295
Haiku 4.5 $0.00009 $0.00147

Measured 6d ago against content hash 4205a0836395, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 6d 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.

Origin

This is a copy

100% identical to boltz — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

configs/microservice/bff-service/configs/agent-skills/claude-science/boltz/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boltz-2

Boltz-2 is the open-weights diffusion co-folder closest in surface to AlphaFold3: a YAML describing protein, DNA, RNA, and ligand chains in, mmCIF plus pTM/ipTM/pLDDT confidences out, with an optional small-molecule affinity head. Among our four co-fold skills it is the default for binder-validation campaigns — fully open MIT weights and the fastest sampler; pick chai1 when you want a second independent model for consensus, openfold3 when AF3-faithful settings matter, and esmfold2 when you can live without an MSA. Code and weights are MIT (PyPI boltz, github.com/jwohlwend/boltz).

Running it

# complex.yaml
version: 1
sequences:
  - protein:
      id: A
      sequence: MVTPEGNVSLVDESLLVGVTDEDRAVRS...   # target
  - protein:
      id: B
      sequence: AIQRTPKIQVYSRHPAENG...            # binder
  - ligand:
      id: L
      smiles: 'N[C@@H](Cc1ccc(O)cc1)C(=O)O'      # or  ccd: SAH
boltz predict complex.yaml \
    --use_msa_server --out_dir out/ --recycling_steps 3 --diffusion_samples 5

Each protein chain needs an MSA; without one the run exits before the model loads. --use_msa_server queries api.colabfold.com (expect a 30–90 s pause per chain) and is the right default unless you already have an .a3m to name under msa: in the YAML. Setting msa: empty forces single-sequence mode — that is an accuracy sacrifice, not a speed or memory optimization, because the MSA search runs on CPU before the GPU stage starts.

Per input the output lands at out/boltz_results_complex/predictions/complex/. Read confidence_complex_model_0.json first: iptm > 0.5 is the community pass line for an interface, complex_plddt > 0.7 for the fold itself, and confidence_score is the weighted aggregate the structures are ranked by. Structures themselves are complex_model_{0..N-1}.cif (or .pdb with --output_format pdb).

Affinity head

Add a properties: block naming one ligand chain as the binder and Boltz-2 predicts protein–small-molecule binding affinity alongside the structure:

Read the full file on GitHub · 123 lines

Files

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.

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. 6d ago First seen · 123 lines · 88 tokens per session scan A 4205a0836395

Subscribe to this mod's changes

boltz is a skill published in the GitHub repository UnicomAI/wanwu (2,456 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 1,475 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to boltz, differing in 18 lines, and is treated as a copy.