Instructions for KDB-X, a computing system for time-series data, vector search, GPU processing, Parquet files, and related modules. It covers q, Python, and SQL use.

Use it for KDB-X modules, vector search, time-series analysis, GPU acceleration, Parquet or Arrow data, REST access, object storage, and module-related errors.

It helps avoid module-loading mistakes and other setup or data-handling errors when working with KDB-X and its extensions.

kdbx — Skill for Claude Code by KxSystems

Install

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.

Any agent

npx skills add KxSystems/kx-skills --skill kdbx

Clone the repo

git clone --depth 1 https://github.com/KxSystems/kx-skills

Made for: Claude Code.

Or install kdbx-knowledge, the plugin that ships this one along with the rest of its 4 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kxsystems/kx-skills/kdbx/github.svg)](https://agentmods.dev/skills/kxsystems/kx-skills/kdbx)

Your own site

<a href="https://agentmods.dev/skills/kxsystems/kx-skills/kdbx"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kdbx/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kxsystems/kx-skills/kdbx"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kdbx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,603 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.01603
Opus 5	$0.00047	$0.00801
Sonnet 5	$0.00019	$0.00321
Haiku 4.5	$0.00009	$0.00160

Measured 9d ago against content hash 3c0f5ed1c357, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

kdbx scanned grade C 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

.kurl.aws.registerByCredentialsFile `:~/.aws/credentials / or register manually

plugins/kdbx-knowledge/skills/kdbx/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KDB-X

Unified compute engine: time-series analytics + vector search + GPU-accelerated compute in one runtime. GA April 2026. Multi-language (q, Python, SQL), native Parquet/Arrow, 25+ community modules. Community Edition free at developer.kx.com.

When to Use

Need	Skill
KDB-X modules, AI libs, Parquet, kURL, GPU, objstor	This skill
q language syntax, operators, table queries	`/q`
KDB-X Python library	`/pykx`
KDB.AI cloud vector database	`/kdbai`

Module Loading

Always use, NEVER \l (\l doesn't bind native functions):

.pq:use`kx.pq              / Parquet        .pq.t:use`kx.pq.t  / Virtual tables
.kurl:use`kx.kurl           / REST client    .ai:use`kx.ai       / AI libraries
.gpu:use`kx.gpu             / GPU accel      .objstor:use`kx.objstor / Object storage
.rest:use`kx.rest           / REST server

Parquet

trades: pq `:trades.parquet                       / Virtual table (row-group pruning)
select from trades where date > 2024.01.01
meta: op `:data.parquet                           / File metadata
vt: (.pq.t:use`kx.pq.t)[`tt] tbl                 / Wrap kdb+ table as virtual

Compression: snappy, gzip, brotli, lz4, zstd.

kURL REST Client

/ .kurl.sync (url; method; options) -> (statusCode; body)
resp:.kurl.sync ("https://api.example.com/data"; `GET; ::)
resp:.kurl.sync ("https://api.example.com"; `POST; enlist[`body]!enlist .j.j data)
resp:.kurl.sync ("https://s3.example.com/f"; `PUT; enlist[`file]!enlist `:path/to/file.csv)
opts:`headers`body!(("Content-Type";"x-api-key")!("application/json";"key123"); .j.j data)
.kurl.async ("https://api.example.com/data"; `GET; enlist[`callback]!enlist (`;{show x}))

/ Auth: .kurl.init`aws then .kurl.register (type; domain; tenant; info)
/ Types: `aws_cred`aws_sts`oauth2`oauth2_jwt`azure`basic
.kurl.aws.registerByCredentialsFile `:~/.aws/credentials  / or register manually

Options: `headers`body`file`callback`service`region

Read the full file on GitHub · 130 lines

Files

What ships with it

2 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.

9d ago First seen · 130 lines · 94 tokens per session scan C 3c0f5ed1c357

Subscribe to this mod's changes

kdbx is a skill published in the GitHub repository KxSystems/kx-skills (16 stars, last pushed 7d ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,603 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Databases RAG and vectors

qdrant

Vector search engine for production RAG systems.

NousResearch/hermes-agent · 13 tokens

chroma

Embedding database for RAG and semantic search.

NousResearch/hermes-agent · 12 tokens

pinecone

Managed vector DB for production RAG and search.

NousResearch/hermes-agent · 13 tokens

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens

pgvector-semantic-search

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…

timescale/pg-aiguide · 190 tokens

postgres-hybrid-text-search

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…

timescale/pg-aiguide · 162 tokens

kdbx