oxy-semantic-layer

oxy-semantic-layer is a cursor rule for coding agents from oxy-hq/skills. It costs 0 tokens per session (4,243 once invoked), scanned A, original, MIT.

A builder for Oxy semantic-layer files: YAML files that describe data tables and business concepts in a form people can query with everyday language.

In plain words
What is it for?
Use it to create or edit views and topics, which define fields, calculations, relationships, and groups of related data for natural-language analytics.
Why use it?
It removes the need to repeatedly hand-write and organize these descriptions, while helping check that the definitions compile and answer queries correctly.

Cursor rule

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 rules/oxy-hq/skills/oxy-semantic-layer
Clone the repo
git clone --depth 1 https://github.com/oxy-hq/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.

agentmods badge for oxy-semantic-layer

README.md
[![agentmods](https://agentmods.dev/badge/rules/oxy-hq/skills/oxy-semantic-layer.svg)](https://agentmods.dev/rules/oxy-hq/skills/oxy-semantic-layer)
Your own site
<a href="https://agentmods.dev/rules/oxy-hq/skills/oxy-semantic-layer"><img src="https://agentmods.dev/badge/rules/oxy-hq/skills/oxy-semantic-layer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 4,243 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 $0.00000 $0.04243
Opus 5 $0.00000 $0.02122
Sonnet 5 $0.00000 $0.00849
Haiku 4.5 $0.00000 $0.00424

Measured 3d ago against content hash b28eb60facee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oxy-semantic-layer 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 3d 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.

cursor/rules/oxy-semantic-layer.mdc · 571 lines

How it starts

The opening of the file, as written. The whole thing — 571 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Oxy Semantic Layer Builder

Build and maintain Oxy semantic layer files (views and topics) that enable business users to query data using natural language.

Core Workflow

  1. Analyze schemas: Read semantics.yml (produced by oxy sync) to understand table structures. If a legacy .databases/ directory exists, read that instead.
  2. Create views: Build semantics/views/*.view.yml files with entities, dimensions, and measures
  3. Create topics: Build semantics/topics/*.topic.yml files to organize views
  4. Validate: Run oxy build to check syntax and compilation (do NOT use oxy validate on view/topic files)
  5. Test: Use oxy semantic-engine --dev-mode to verify queries work

View File Structure

Views are the core of the semantic layer. Each view file (semantics/views/*.view.yml) defines:

name: view_name
description: "Clear business explanation of what this view represents"
datasource: "database_name"  # Must match config.yml
table: "schema_name.table_name"

entities:
  - name: entity_name
    type: primary|foreign
    description: "What this entity represents"
    key: dimension_name  # MUST reference a dimension name, not a column

dimensions:
  - name: dimension_name
    type: string|number|date|datetime|boolean
    description: "Business-friendly explanation"
    expr: column_name_or_sql_expression
    samples: ["example1", "example2"]  # Optional but helpful
    synonyms: ["alias1", "alias2"]     # For natural language queries

measures:
  - name: measure_name
    type: sum|average|count|count_distinct|min|max|median|stddev|custom
    description: "What this metric represents"
    expr: column_name_or_sql_expression
    synonyms: ["alternative name"]
    filters: []  # Optional, for filtered measures

Entity Design (Critical for Joins)

Entities enable automatic joins between views. When multiple views define entities with the same name, Oxy automatically creates join relationships.

Entity Types

  • Primary entity: The main subject of the view (one per view, required)
  • Foreign entity: References to objects in other views (creates relationships)

Read the full file on GitHub · 571 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. 3d ago First seen · 571 lines · 0 tokens per session scan A b28eb60facee

Subscribe to this mod's changes

oxy-semantic-layer is a cursor rule published in the GitHub repository oxy-hq/skills (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,243 tokens. 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.