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 001TMF/blatant-why --skill boltzgengit clone --depth 1 https://github.com/001TMF/blatant-whyWrote 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/001tmf/blatant-why/boltzgen)<a href="https://agentmods.dev/skills/001tmf/blatant-why/boltzgen"><img src="https://agentmods.dev/badge/skills/001tmf/blatant-why/boltzgen/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/001tmf/blatant-why/boltzgen"><img src="https://agentmods.dev/badge/skills/001tmf/blatant-why/boltzgen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00003 | $0.06442 |
| Opus 5 | $0.00002 | $0.03221 |
| Sonnet 5 | $0.00001 | $0.01288 |
| Haiku 4.5 | $0.00000 | $0.00644 |
Grade A, and why
boltzgen 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 9d 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.
- ❌ Write inline `subprocess.run(["boltzgen", ...])` calls → use `boltzgen_submit.py` How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BoltzGen — Antibody / Nanobody / Binder Design
BoltzGen is an all-atom diffusion model that generates antibody, nanobody,
and de novo miniprotein backbones conditioned on a target structure and a
set of binding (hotspot) residues. Sequences are assigned by AntiFold, then
each design is independently refolded with Protenix to produce ipTM, pTM,
pLDDT, ipSAE, and CA-RMSD metrics. This skill teaches the exact
Write → Bash → Read pattern for invoking BoltzGen via its CLI on local
GPU (default), HPC (RunPod via by-deploy-compute), or Tamarind cloud.
The legacy CLI name was proteus-ab. It has been renamed to BoltzGen
throughout. If you see proteus-ab in older docs or scripts, treat it as
the same engine — the binary on PATH is now boltzgen.
When to Use This Skill
Use BoltzGen when you have:
- ✅ A cleaned target structure (CIF or PDB) with unambiguous chain IDs
- ✅ A defined epitope or hotspot set expressed in
label_seq_idnumbering - ✅ A modality decision in hand — VHH single-domain, full antibody Fab, or de novo miniprotein
- ✅ GPU compute available — local (CUDA-capable, ≥24 GB VRAM), HPC (RunPod), or Tamarind cloud
- ✅ A design budget — typical preview is 10–20 designs; production is 50–200
Do NOT use BoltzGen when:
- ❌ You need to validate a known antibody sequence against a target → use Protenix directly (no design needed)
- ❌ You need to score or filter an existing batch of designs → use by-scoring (ipSAE) and by-screening
- ❌ No epitope is known or characterised → run by-research + by-epitope-analysis first; designing with no
binding_typesis wasteful - ❌ You want a small-molecule binder → BoltzGen designs proteins/peptides only
- ❌ You need ranked, published results → use by-display /
/by:results
Quick Start
A 20-design VHH preview against TNF-α (PDB 1TNF, epitope residues 45–52 and 78–85) on a local GPU:
# Step 1: write spec via the Write tool — see scripts/boltzgen_submit.py for a builder
# Step 2: submit (dry-run prints the command; remove --dry-run to launch)
python scripts/boltzgen_submit.py \
--spec workspace/tnf_spec.yaml \
--protocol nanobody-anything \
--num-designs 20 \
--budget 48 \
--target local \
--output workspace/tnf_out
# Step 3: parse results into a CSV with sequences + metrics
python scripts/parse_designs.py \
--output-dir workspace/tnf_out \
--csv workspace/tnf_designs.csv
What ships with it
5 files 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.
- 9d ago First seen · 473 lines · 3 tokens per session scan A 3e84c7c542b4
boltzgen is a skill published in the GitHub repository 001TMF/blatant-why (114 stars, last pushed 23d ago), licensed MIT. It adds 3 tokens to every session and 6,442 once invoked, about $0.0000 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
alphafold
Skill for protein structure prediction and analysis with AlphaFold. Use this skill whenever a user wants to predict or fetch a protein 3D structure, download structures from the AlphaFold Database (AFDB), run ColabFold for novel proteins, parse pLDDT confidence scores or PAE (predicted aligned error) from AlphaFold…
esm2
Skill for working with ESM2 protein language models from Meta FAIR. Use this skill whenever the user wants to generate protein embeddings or representations, score variant effects or predict mutation fitness, run contact prediction, or use ESMFold for structure prediction. Also trigger when the user mentions ESM2…
evo2
Skill for genomic sequence modeling and design with Evo2 from Arc Institute. Use this skill when a user wants to model or generate DNA sequences, score variant effects at single-nucleotide resolution, extract genomic embeddings, analyze mutations in non-coding or coding regions, design synthetic genomic elements…
rfdiffusion
Skill for de novo protein backbone generation with RFdiffusion from the Baker Lab (Institute for Protein Design). Use this skill when a user wants to design a new protein backbone from scratch, scaffold a functional motif into a new protein, design a protein binder against a target, generate symmetric oligomers…
alphafold3
Skill for structure prediction with AlphaFold 3 (AF3) from Google DeepMind. Use this skill when a user wants to predict the structure of a protein complex with ligands, DNA, or RNA; predict protein-ligand binding poses; model protein-nucleic acid interactions; use SMILES or CCD codes to specify small molecules; parse…
boltz
Skill for biomolecular structure and binding affinity prediction with Boltz-2. Use this skill when a user wants to predict protein-ligand complex structures, estimate binding affinities (IC50/ΔG), screen compound libraries, optimize lead compounds, model protein-DNA or protein-RNA interactions, specify binding pockets…