oxy:build-instance

A command that creates a complete Oxy analytics project from an empty project directory. It can set up the semantic layer, workflows, agents, optional data loading, and an executive dashboard.

In plain words
What is it for?
Use it to start a full Oxy analytics instance from scratch, with the option to skip the data-loading pipeline.
Why use it?
It coordinates the main setup tasks in order, checking the environment and creating missing configuration before building. This avoids assembling each part manually.

Command

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.

agentmods
npx agentmods add commands/oxy-hq/skills/build-instance
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/skills
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,113 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00049 $0.02113
Opus 5 $0.00024 $0.01056
Sonnet 5 $0.00010 $0.00423
Haiku 4.5 $0.00005 $0.00211

Measured 2d ago against content hash 40f331937b69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oxy:build-instance 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 2d 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.

commands/build-instance.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Oxy Instance

Build a complete Oxy analytics instance by running the 4 core skills in sequence: semantic layer → workflows & agents → ETL pipeline (optional) → dashboard app.

Parse the argument: if --no-etl was passed, skip Step 4 (ETL).


Step 1: Environment Setup

Before building anything, verify the project is properly configured. If anything is missing, pause and help the user set it up before continuing.

1a. Check for config.yml

Run: ls config.yml 2>/dev/null && echo "EXISTS" || echo "MISSING"

If MISSING, create it now. Ask the user which database type they are using, then generate a config.yml using the appropriate template below:

ClickHouse (e.g. restaurant analytics):

# yaml-language-server: $schema=https://raw.githubusercontent.com/oxy-hq/oxy/refs/heads/main/json-schemas/config.json
defaults:
  database: clickhouse

models:
  - vendor: openai
    name: openai-4.1
    model_ref: gpt-4.1
    key_var: OPENAI_API_KEY
    api_url: https://api.openai.com/v1

  - vendor: anthropic
    name: claude-sonnet-4-6
    model_ref: claude-sonnet-4-6
    key_var: ANTHROPIC_API_KEY

databases:
  - name: clickhouse
    type: clickhouse
    host_var: CLICKHOUSE_HOST
    user_var: CLICKHOUSE_USERNAME
    password_var: CLICKHOUSE_PASSWORD
    database_var: CLICKHOUSE_DATABASE
    schemas:
      your_schema_name:
        - "your_schema_name___*"   # adjust to match your table prefix pattern

Snowflake (e.g. HubSpot / enterprise):

# yaml-language-server: $schema=https://raw.githubusercontent.com/oxy-hq/oxy/refs/heads/main/json-schemas/config.json
databases:
  - name: snowflake
    type: snowflake
    account: YOUR_ACCOUNT_IDENTIFIER   # e.g. SW55517-HUBSPOT
    username: [email protected]
    warehouse: YOUR_WAREHOUSE
    database: YOUR_DATABASE
    role: YOUR_ROLE

models:
  - name: openai
    vendor: openai
    model_ref: gpt-4.1
    key_var: OPENAI_API_KEY

1b. Check for .env

Run: ls .env 2>/dev/null && echo "EXISTS" || echo "MISSING"

Read the full file on GitHub · 277 lines

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. 2d ago First seen · 277 lines · 49 tokens per session scan A 40f331937b69

Subscribe to this mod's changes

oxy:build-instance is a command published in the GitHub repository oxy-hq/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 2,113 once invoked, about $0.0002 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.