jgi-lakehouse

jgi-lakehouse is a skill for Claude Code, Codex from openscientist-io/openscientist. It costs 88 tokens per session (939 once invoked), scanned A, original, Apache-2.0.

A set of tools for querying JGI’s Dremio Lakehouse, a data platform containing genomics databases such as GOLD and IMG. It supports SQL queries and structured result formats.

In plain words
What is it for?
Use it to explore tables and schemas, query GOLD studies or IMG data, join related records, and export results as JSON, CSV, or YAML.
Why use it?
It avoids manually browsing large genomics datasets and makes it possible to retrieve only the records needed for analysis.

Skill for Claude CodeCodex

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

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/cjm/repos/linkml-store/jgi-lakehouse-analysis/.

Good fit Use it to explore tables and schemas, query GOLD studies or IMG data, join related records, and export results as JSON, CSV, or YAML.

Compare 6 skills from other repositories ↓
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 jgi-lakehouse

README.md
[![agentmods](https://agentmods.dev/badge/skills/openscientist-io/openscientist/jgi-lakehouse/github.svg)](https://agentmods.dev/skills/openscientist-io/openscientist/jgi-lakehouse)
Your own site
<a href="https://agentmods.dev/skills/openscientist-io/openscientist/jgi-lakehouse"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/jgi-lakehouse/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.

agentmods 80×15 button for jgi-lakehouse

Your own site · 80×15
<a href="https://agentmods.dev/skills/openscientist-io/openscientist/jgi-lakehouse"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/jgi-lakehouse.svg" alt="Reviewed on agentmods" width="80" 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 939 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00088 $0.00939
Opus 5 $0.00044 $0.00469
Sonnet 5 $0.00018 $0.00188
Haiku 4.5 $0.00009 $0.00094

Measured 10d ago against content hash fdc59582eeb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

jgi-lakehouse 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 10d 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.

skills/domain/berkeley-data-lakehouse/jgi-lakehouse/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JGI Lakehouse Query

Query the JGI Dremio Lakehouse via CLI.

Setup

pip install linkml-store[dremio]
export DREMIO_USER="your_username"
export DREMIO_PASSWORD="your_password"

Connection

# Base connection (no schema filter)
DB="dremio-rest://lakehouse.jgi.lbl.gov"

# GOLD database
GOLD="dremio-rest://lakehouse.jgi.lbl.gov?schema=gold-db-2 postgresql.gold"

# IMG Core database
IMG="dremio-rest://lakehouse.jgi.lbl.gov?schema=img-db-2 postgresql.img_core_v400"

SQL Queries

Direct SQL via --sql flag:

# Query GOLD studies
linkml-store -d "$DB" query --sql 'SELECT * FROM "gold-db-2 postgresql".gold.study LIMIT 10'

# Count by ecosystem
linkml-store -d "$DB" query --sql 'SELECT ecosystem, COUNT(*) as cnt FROM "gold-db-2 postgresql".gold.study GROUP BY ecosystem ORDER BY cnt DESC'

# Join tables
linkml-store -d "$DB" query --sql 'SELECT s.study_name, p.project_name FROM "gold-db-2 postgresql".gold.study s JOIN "gold-db-2 postgresql".gold.project p ON s.study_id = p.study_id LIMIT 10'

# Output formats
linkml-store -d "$DB" query --sql '...' -O json
linkml-store -d "$DB" query --sql '...' -O csv
linkml-store -d "$DB" query --sql '...' -O yaml

Collection Queries

When schema is set, use collection-based queries:

# List tables
linkml-store -d "$GOLD" list-collections

# Query collection
linkml-store -d "$GOLD" -c study query --limit 10

# With filter
linkml-store -d "$GOLD" -c study query -w "ecosystem=Host-associated" --limit 20

# Describe table
linkml-store -d "$GOLD" -c study describe

Schema Export

# Export LinkML schema with FK relationships
linkml-store -d "$GOLD" schema -O yaml -o gold.linkml.yaml

Key Databases

Schema Path Tables Description
"gold-db-2 postgresql".gold 42 GOLD - genome project metadata
"img-db-2 postgresql".img_core_v400 244 IMG Core - genes, taxa, annotations
"img-db-2 postgresql".img_ext 84 IMG Extended data
"img-db-2 postgresql".img_sat_v450 141 IMG Satellite/experimental

Read the full file on GitHub · 107 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. 10d ago First seen · 107 lines · 88 tokens per session scan A fdc59582eeb9

Subscribe to this mod's changes

jgi-lakehouse is a skill published in the GitHub repository openscientist-io/openscientist (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 939 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

lamindb

Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations.

K-Dense-AI/scientific-agent-skills · 56 tokens

tiledbvcf

Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.

K-Dense-AI/scientific-agent-skills · 46 tokens

defining-cohort-phenotypes

Authors computable phenotype and cohort definitions in the OHDSI ATLAS / CIRCE style over the OMOP CDM, combining standard concept sets with NLP-derived features that OpenMed extracts. Use when the user wants to define a patient cohort, write a computable phenotype, reuse PheKB or OHDSI Phenotype Library logic, build…

maziyarpanahi/openmed · 191 tokens

benchling-integration

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

synthetic-sciences/openscience · 44 tokens

chembl-database

Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.

google-deepmind/science-skills · 53 tokens

nvalchemi-data-storage

How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, Reader, Dataset, MultiDataset, DataLoader). Use when saving simulation outputs or trajectories to disk, converting structures (e.g. ASE / extxyz) into Zarr stores, assembling datasets for training or…

NVIDIA/nvalchemi-toolkit · 90 tokens