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 adaptyvbio/protein-design-skills --skill foldseekgit clone --depth 1 https://github.com/adaptyvbio/protein-design-skillsWrote 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/adaptyvbio/protein-design-skills/foldseek)<a href="https://agentmods.dev/skills/adaptyvbio/protein-design-skills/foldseek"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/foldseek/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/adaptyvbio/protein-design-skills/foldseek"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/foldseek.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Output Handling · line 60 Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
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 | $0.00090 | $0.01321 |
| Opus 5 | $0.00045 | $0.00660 |
| Sonnet 5 | $0.00018 | $0.00264 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
foldseek scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://search.foldseek.com/api/ticket" \ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foldseek Structure Search
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Python | 3.8+ | 3.10 |
| RAM | 8GB | 16GB |
| Disk | 10GB | 50GB (for local databases) |
How to run
Note: Foldseek can run locally or via web server. No GPU required.
Option 1: Web Server (Quick; rate-limited, use sparingly)
# Upload structure to web server
curl -X POST "https://search.foldseek.com/api/ticket" \
-F "[email protected]" \
-F "database[]=afdb50" \
-F "database[]=pdb100"
Option 2: Local installation
# Install Foldseek
conda install -c conda-forge -c bioconda foldseek
# Search PDB
foldseek easy-search query.pdb /path/to/pdb100 results.m8 tmp/
# Search AlphaFold DB
foldseek easy-search query.pdb /path/to/afdb50 results.m8 tmp/
Option 3: Python API
import subprocess
import pandas as pd
def foldseek_search(query_pdb, database, output="results.m8"):
"""Run Foldseek search."""
subprocess.run([
"foldseek", "easy-search",
query_pdb, database, output, "tmp/",
"--format-output", "query,target,pident,alnlen,evalue,bits"
])
return pd.read_csv(output, sep="\t",
names=["query", "target", "pident", "alnlen", "evalue", "bits"])
Key parameters
| Parameter | Default | Description |
|---|---|---|
--min-seq-id |
0.0 | Minimum sequence identity |
-e |
0.001 | E-value threshold |
--alignment-type |
2 | 0=3Di, 1=TM, 2=3Di+AA |
--max-seqs |
1000 | Max hits to pass through prefilter; reducing this affects sensitivity |
Databases
| Database | Description | Size |
|---|---|---|
pdb100 |
PDB chains | ~340K structures |
afdb50 |
AlphaFold DB clustered at 50% sequence identity | ~53M structures |
swissprot |
SwissProt structures | ~540K structures |
cath50 |
CATH domains | ~50K domains |
Output format
# results.m8 (tabular)
query target pident alnlen evalue bits
query 1abc_A 85.2 120 1e-45 180.5
query 2def_B 72.1 115 1e-32 145.2
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.
- 11d ago First seen · 176 lines · 90 tokens per session scan A 3503be2b0cc1
foldseek is a skill published in the GitHub repository adaptyvbio/protein-design-skills (158 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,321 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, 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
foldseek
Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot…
foldseek
Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot…
foldseek
Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot…
pdb
Fetch and analyze protein structures from RCSB PDB. Use this skill when: (1) Need to download a structure by PDB ID, (2) Search for similar structures, (3) Prepare target for binder design, (4) Extract specific chains or domains, (5) Get structure metadata. For sequence lookup, use uniprot. For binder design workflow…
pdb
Fetch and analyze protein structures from RCSB PDB. Use this skill when: (1) Need to download a structure by PDB ID, (2) Search for similar structures, (3) Prepare target for binder design, (4) Extract specific chains or domains, (5) Get structure metadata. For sequence lookup, use uniprot. For binder design workflow…
structure-search
Structure-based similarity search and scaffold analysis for drug discovery. Use for lead hopping, scaffold morphing, and chemical space exploration. Keywords: similarity search, scaffold hopping, chemical space, fingerprint, Tanimoto.