alphafold

alphafold is a skill for Claude Code, Codex from naity/FM4Life. It costs 141 tokens per session (2,634 once invoked), scanned A, original, MIT.

A skill for predicting and examining the three-dimensional shape of proteins using AlphaFold, an AI system for protein-structure prediction. It can fetch existing predictions or support predictions for new protein sequences.

In plain words
What is it for?
Use it to retrieve structures from the AlphaFold Database, run ColabFold for new sequences, use local AlphaFold 2 for batch or high-performance-computing work, or inspect confidence scores and prediction-error data.
Why use it?
It helps researchers obtain a likely protein structure without building the full prediction workflow from scratch.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 docker/run_docker.py \.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 alphafold

README.md
[![agentmods](https://agentmods.dev/badge/skills/naity/fm4life/alphafold.svg)](https://agentmods.dev/skills/naity/fm4life/alphafold)
Your own site
<a href="https://agentmods.dev/skills/naity/fm4life/alphafold"><img src="https://agentmods.dev/badge/skills/naity/fm4life/alphafold.svg" alt="Measured on agentmods" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,634 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00141 $0.02634
Opus 5 $0.00071 $0.01317
Sonnet 5 $0.00028 $0.00527
Haiku 4.5 $0.00014 $0.00263

Measured 6d ago against content hash 891bd6ac029b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

alphafold 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_afdb.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

response = requests.get(url)
skills/alphafold/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlphaFold: Protein Structure Prediction

Overview

AlphaFold is DeepMind's protein structure prediction system. Most users don't need to install AlphaFold locally — there are faster, lighter alternatives that cover the majority of use cases:

Need Best approach
Known UniProt protein AFDB API — fetch precomputed structure instantly
Novel protein sequence ColabFold — no local databases needed
Novel protein, batch/HPC Local AF2 (Docker) — full pipeline
Protein + DNA/RNA/ligand AlphaFold3 (web server or local)
Fast, no MSA ESMFold (see skills/esm2)

Approach 1: AlphaFold Database (AFDB) API

The AFDB covers >200 million proteins from UniRef90 with precomputed structures. If your protein has a UniProt accession, fetch it in seconds — no GPU, no installation.

import requests

def fetch_afdb_structure(uniprot_id: str, output_dir: str = ".") -> dict:
    """
    Fetch AlphaFold structure for a UniProt ID.
    Returns metadata dict with paths to downloaded files.
    """
    from pathlib import Path

    # Get prediction metadata
    url = f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}"
    response = requests.get(url)
    response.raise_for_status()
    prediction = response.json()[0]  # list with one entry

    out_dir = Path(output_dir)
    out_dir.mkdir(parents=True, exist_ok=True)
    downloaded = {}

    # Download PDB
    pdb_url = prediction["pdbUrl"]
    pdb_path = out_dir / f"{uniprot_id}.pdb"
    pdb_path.write_bytes(requests.get(pdb_url).content)
    downloaded["pdb"] = str(pdb_path)

    # Download PAE JSON (pairwise confidence)
    if pae_url := prediction.get("paeDocUrl"):
        pae_path = out_dir / f"{uniprot_id}_pae.json"
        pae_path.write_bytes(requests.get(pae_url).content)
        downloaded["pae"] = str(pae_path)

    print(f"Downloaded {uniprot_id}: {pdb_path}")
    print(f"  pLDDT (mean): {prediction.get('globalMetricValue', 'N/A'):.1f}")
    print(f"  Model: {prediction.get('modelCreatedDate', 'N/A')}")
    return downloaded

# Example
files = fetch_afdb_structure("P00533")  # EGFR

Read the full file on GitHub · 260 lines

Files

What ships with it

3 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.

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 · 260 lines · 141 tokens per session scan A 891bd6ac029b

Subscribe to this mod's changes

alphafold is a skill published in the GitHub repository naity/FM4Life (2 stars, last pushed 5mo ago), licensed MIT. It adds 141 tokens to every session and 2,634 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

cibersort-immune-infiltration-analysis

Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq…

aipoch/medical-research-skills · 92 tokens

gene-protein-expression-matrix-normalization

Use when normalizing bulk gene or protein expression matrices with log2 transform, z-score standardization, or min-max scaling before downstream visualization or exploratory analysis. NOT for count-model normalization such as TPM/DESeq2 size factors, batch correction, or single-cell preprocessing.

aipoch/medical-research-skills · 63 tokens

by-campaign-optimizer

Multi-round design campaigns generate scored designs at every iteration. This skill turns that scoring history into actionable parameter changes for the next round — training a lightweight Random Forest on the designs you already have, ranking which features actually discriminate good from bad, and proposing…

001TMF/blatant-why · 5 tokens

protenix

Protenix v1 is an AF3-class structure prediction model (368M parameters) for proteins, complexes, and protein-ligand systems. This skill wraps the protenix CLI with a documented input spec, an input-validating Python entry point, and a multi-seed ensemble aggregator so that callers can drive predictions through…

001TMF/blatant-why · 3 tokens

fragment-based-count-matrix-generation

Use when you have a backed AnnData object containing processed fragment data (stored in .obsm['fragmentpaired'] or .

HolobiomicsLab/asb-skill-collections · 33 tokens

methylbase-object-handling

Use when after reading in per-sample methylation call files with methRead() and obtaining methylRawList objects, but before calculating differential methylation or performing annotation.

HolobiomicsLab/asb-skill-collections · 40 tokens