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 naity/FM4Life --skill alphafold3git clone --depth 1 https://github.com/naity/FM4LifeWrote 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/naity/fm4life/alphafold3)<a href="https://agentmods.dev/skills/naity/fm4life/alphafold3"><img src="https://agentmods.dev/badge/skills/naity/fm4life/alphafold3.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00151 | $0.02395 |
| Opus 5 | $0.00076 | $0.01197 |
| Sonnet 5 | $0.00030 | $0.00479 |
| Haiku 4.5 | $0.00015 | $0.00239 |
Grade A, and why
alphafold3 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaFold 3: Biomolecular Structure Prediction
Overview
AlphaFold 3 predicts the structure of mixed biomolecular systems in a single unified model:
- Proteins (including post-translational modifications)
- RNA and DNA (including modified bases)
- Small molecule ligands (via CCD codes or SMILES)
- Ions and cofactors
- Covalently modified residues
This makes AF3 the tool of choice when your system contains anything beyond a bare protein. For pure protein structure prediction, AlphaFold 2 / ColabFold remains widely used and well-benchmarked.
⚠️ License and Access
AF3 is non-commercial only. Key constraints:
- Source code: CC-BY-NC-SA 4.0 — non-commercial use only
- Model weights: separate terms of use — must apply directly from Google; commercial use requires a separate agreement
- Outputs: subject to output terms of use
For commercial use, check with Google DeepMind directly.
Access Options
Option 1: Web Server (fastest, no install)
https://alphafoldserver.com — free, up to 20 jobs/day, no installation required. Best for:
- Exploratory work
- Single predictions
- Proteins + limited ligand set
The web server uses a slightly simplified JSON format (alphafoldserver dialect) and has a more limited set of ligands and covalent modifications than the local install.
Option 2: Local Install (full capabilities)
Requires:
- Linux (Ubuntu 22.04 recommended)
- NVIDIA GPU with Compute Capability ≥ 8.0 (A100 or H100 80GB)
- ≥ 64 GB RAM
- ~1 TB disk for databases (SSD recommended)
- Model weights from Google (apply here)
# Clone and build Docker image
git clone https://github.com/google-deepmind/alphafold3.git && cd alphafold3
docker build -t alphafold3 -f docker/Dockerfile .
# Download databases (~600 GB download)
bash fetch_databases.sh /data/af3_databases
# Run prediction
docker run -it \
--volume $HOME/af_input:/root/af_input \
--volume $HOME/af_output:/root/af_output \
--volume /data/af3_models:/root/models \
--volume /data/af3_databases:/root/public_databases \
--gpus all \
alphafold3 \
python run_alphafold.py \
--json_path=/root/af_input/input.json \
--model_dir=/root/models \
--output_dir=/root/af_output
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.
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.
- 7d ago First seen · 269 lines · 151 tokens per session scan A 7c58d479dbc4
alphafold3 is a skill published in the GitHub repository naity/FM4Life (2 stars, last pushed 5mo ago), licensed MIT. It adds 151 tokens to every session and 2,395 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
estimate-immune-score-analysis
Use this skill to compute ESTIMATE immune-related microenvironment scores from a bulk expression matrix, generate an ESTIMATE score heatmap, and optionally generate group-wise ESTIMATE score boxplots plus significance tables when a sample group file is supplied. Trigger keywords: ESTIMATE, immune score, stromal score…
external-model-validation
Use when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk distribution plots, heatmap, and time-dependent ROC curves. NOT for: model training, feature selection, nomogram construction, calibration analysis…
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…
medical-research-literature-reader-pro
A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title.…
adverse-event-narrative
Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.
anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.