sigma-data-models

sigma-data-models is a cursor rule for Cursor from twells89/sigma-migration-skills. It costs 166 tokens per session (2,022 once invoked), scanned A, original, MIT.

Instructions for creating, reading, and editing Sigma data models through Sigma's REST API, using definitions that describe tables, fields, calculations, relationships, filters, and permissions.

In plain words
What is it for?
Use them to expose warehouse tables, add metrics or relationships, change sources, edit columns, and exchange model definitions with Sigma.
Why use it?
They make data-model changes repeatable in code and clarify that conversions from other analytics tools require a separate converter.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

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/twells89/sigma-migration-skills/sigma-data-models
Clone the repo
git clone --depth 1 https://github.com/twells89/sigma-migration-skills

Made for: Cursor.

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 sigma-data-models

README.md
[![agentmods](https://agentmods.dev/badge/rules/twells89/sigma-migration-skills/sigma-data-models.svg)](https://agentmods.dev/rules/twells89/sigma-migration-skills/sigma-data-models)
Your own site
<a href="https://agentmods.dev/rules/twells89/sigma-migration-skills/sigma-data-models"><img src="https://agentmods.dev/badge/rules/twells89/sigma-migration-skills/sigma-data-models.svg" alt="Measured on agentmods" height="20"></a>
Per session 166 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,022 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00166 $0.02022
Opus 5 $0.00083 $0.01011
Sonnet 5 $0.00033 $0.00404
Haiku 4.5 $0.00017 $0.00202

Measured 6d ago against content hash e5062e3464a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sigma-data-models scanned grade A 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 6d 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.

**Requirements:** `curl`, `jq`, `base64`. Your Sigma API credentials must have permission to create or edit data models, plus "Can edit" access on the destination folder (for create) or the existing data model (for updat
plugins/sigma-authoring/skills/sigma-data-models/generated/cursor/rules/sigma-data-models.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Author, retrieve, or modify a Sigma data model spec (the JSON/YAML semantic-layer definition with sources, columns, metrics, relationships, filters, controls, folder groupings, and column-level security) by calling the Sigma REST API directly. Use when the user wants to build a new data model from existing warehouse tables, add metrics or relationships to an existing model, change a model's source, edit columns, or round-trip a data model spec through code. Out of scope: converting from another BI tool's format (dbt, LookML, Tableau, Power BI, Alteryx, etc.). Those conversions are handled by the Sigma data-model converter (browser tool + MCP) — point users there when they paste source-format input. Requires an SIGMA_API_TOKEN — obtain via the sigma-api skill first.

Sigma Data Models (Author / Get / Update)

Build a Sigma data model spec — the JSON definition of pages, sources, columns, metrics, relationships, filters, controls, folder groupings, and column-level security — and round-trip it through the Sigma REST API.

This skill is for authoring from existing warehouse tables: a user knows their warehouse, wants to expose specific tables as a Sigma data model with the right joins, metrics, and governance, and needs help composing the spec. Conversions from other BI-tool formats (dbt schema.yml, LookML views, Tableau TDS, Power BI PBIT, Alteryx YXMD, etc.) are not in this skill — direct users to the Sigma data-model converter MCP / browser tool, which already handles those mappings.

Auth: Authenticate via the sigma-api skill first to set $SIGMA_BASE_URL and $SIGMA_API_TOKEN. This skill assumes both are already exported.

Requirements: curl, jq, base64. Your Sigma API credentials must have permission to create or edit data models, plus "Can edit" access on the destination folder (for create) or the existing data model (for update). If a request returns 403, ask your Sigma admin to confirm the credential's permissions.

Read the full file on GitHub · 83 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. 6d ago First seen · 83 lines · 166 tokens per session scan A e5062e3464a4

Subscribe to this mod's changes

sigma-data-models is a cursor rule published in the GitHub repository twells89/sigma-migration-skills (14 stars, last pushed 2d ago), licensed MIT. It adds 166 tokens to every session and 2,022 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.