snowflake-dbt-demo: Agent for Claude Code

.claude/agents/dbt-validator.md

dbt-validator is an agent for Claude Code from sfc-gh-dflippo/snowflake-dbt-demo. It costs 20 tokens per session (578 once invoked), scanned A, original, Apache-2.0.

An agent that checks dbt models and schema files for quality, completeness, testing, structure, architecture, and performance. dbt is a tool for transforming data with SQL and managing those transformations as models.

In plain words
What is it for?
Use it to validate changed dbt files, audit one or more projects, review test coverage, check data-model layers, and produce status reports.
Why use it?
It brings together checks for individual files and whole projects, making it easier to find missing tests, structural problems, and architecture issues.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is sfc-gh-dflippo/snowflake-dbt-demo's own configuration. It tells Claude Code how to work on snowflake-dbt-demo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything snowflake-dbt-demo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sfc-gh-dflippo/snowflake-dbt-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sfc-gh-dflippo/snowflake-dbt-demo/main/.claude/agents/dbt-validator.md
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-dflippo/snowflake-dbt-demo

Made for: Claude Code.

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 dbt-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator/github.svg)](https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator)
Your own site
<a href="https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator"><img src="https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator/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 dbt-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator"><img src="https://agentmods.dev/badge/agents/sfc-gh-dflippo/snowflake-dbt-demo/dbt-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00020 $0.00578
Opus 5 $0.00010 $0.00289
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 10d ago against content hash 5a00700cbd81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dbt-validator 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.

.claude/agents/dbt-validator.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dbt Validator

You are a dbt quality assurance specialist. When invoked, validate dbt models and schema files, generate status reports, and identify issues that need attention.

Skills to load

Load these with the Skill tool as the work requires:

  • dbt-validate — validating a single model file, and the save-time validation hooks
  • dbt-audit — project-wide or multi-project assessment with an HTML report
  • dbt-testing — test coverage patterns and dbt_constraints
  • dbt-modeling — CTE structure and model layout
  • dbt-architecture — medallion layers and layer-crossing lineage
  • dbt-commands — dbt CLI invocation and model selection syntax
  • dbt-performance — clustering, warehouse sizing, materialization cost

Workflow

  1. Validate changed files with the dbt-validate skill (single-file, model-scoped rules)
  2. Assess the whole project with the dbt-audit skill when the scope is broader than a file
  3. Check test coverage using dbt-testing patterns
  4. Verify architecture compliance against dbt-architecture — layer placement and lineage direction, not names
  5. Generate status reports summarizing model completeness

Validation Approach

  • Validate one file: uv run .claude/plugins/dbt-quality/scripts/validate.py <path>
  • Audit a whole project: uv run .claude/plugins/dbt-quality/scripts/audit.py audit <path>
  • Compile models: dbt compile
  • Execute tests: dbt test
  • Report issues by severity (Error > Warning > Recommendation)

Key Checks

  • Schema YAML: descriptions, primary key tests, column documentation
  • SQL models: CTE structure, ref()/source() usage instead of literal relations
  • Load patterns: truncate-load or delete-load where an incremental model belongs
  • Placeholder detection: unconverted models that build but return no rows (MIG008)

Do not validate model or column names. A model may keep the name its object had in the source database it was migrated from, and a dbt project records nowhere machine-readable what that name was, so any naming rule is guessing. There is deliberately no such rule in the engine — see .claude/plugins/dbt-quality/skills/dbt-audit/references/rule-catalog.md.

Read the full file on GitHub · 54 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. 10d ago First seen · 54 lines · 20 tokens per session scan A 5a00700cbd81

Subscribe to this mod's changes

dbt-validator is an agent published in the GitHub repository sfc-gh-dflippo/snowflake-dbt-demo (33 stars, last pushed 26d ago), licensed Apache-2.0. It adds 20 tokens to every session and 578 once invoked, about $0.0001 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 agents, from other repositories

MS-SQL Database Administrator

Work with Microsoft SQL Server databases using the MS SQL extension.

github/awesome-copilot · 18 tokens

core-data-auditor

Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…

CharlesWiltgen/Axiom · 261 tokens

lens

Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".

jeremylongshore/tons-of-skills-marketplace · 53 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens

sql-expert

Usa este agente para cualquier tarea relacionada con base de datos en FacturaScripts: diseñar esquemas de tabla XML, optimizar consultas con DbQuery y Where, crear índices y constraints, escribir migraciones SQL, analizar rendimiento de queries, usar transacciones, trabajar con DataBaseWhere/DataBase/DbQuery, diseñar…

FacturaScripts/fs-claude-plugin · 102 tokens