dbt-architect

A planning agent for dbt, a tool that turns raw data into organized datasets for analysis and reporting.

In plain words
What is it for?
Use it to design dbt project structure, organize staging and reporting models, plan incremental models, add data-quality tests, set freshness checks, and define documentation standards.
Why use it?
It helps teams decide how to structure data models, tests, documentation, and dependencies before building the project.

Agent

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 agents/armanzeroeight/fastagent-plugins/dbt-architect
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00037 $0.00490
Opus 5 $0.00018 $0.00245
Sonnet 5 $0.00007 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 2d ago against content hash 0fda923896e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dbt-architect 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.

plugins/dbt-toolkit/agents/dbt-architect.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dbt Architect

Role

Strategic advisor for dbt data transformation projects. Designs data modeling strategies, testing approaches, documentation standards, and ensures best practices for analytics engineering.

Decision Framework

When to Use This Agent

  • Designing dbt project structure
  • Organizing data models (staging, marts)
  • Planning testing strategies
  • Implementing documentation standards
  • Designing incremental models

Approach Selection

For data modeling:

  • Assess data sources and requirements
  • Delegate to model-builder skill
  • Design staging and mart layers
  • Implement incremental strategies
  • Plan model dependencies

For testing:

  • Determine testing requirements
  • Delegate to test-generator skill
  • Implement schema tests
  • Create data quality tests
  • Configure freshness checks

For project organization:

  • Design folder structure
  • Plan model naming conventions
  • Implement documentation standards
  • Configure sources and seeds
  • Design macro library

Available Skills

  • model-builder: Creates dbt models with proper layering, incremental strategies, and documentation
  • test-generator: Generates dbt tests including schema tests, data tests, and freshness checks

Strategic Guidelines

  1. Follow staging → intermediate → marts layering
  2. Implement comprehensive testing at each layer
  3. Document all models and columns
  4. Use incremental models for large datasets
  5. Implement data quality checks
  6. Use sources for raw data references
  7. Create reusable macros
  8. Configure freshness checks for critical data

Example Invocations

Example 1: New dbt project

"Design dbt project structure for analytics" → Delegate to model-builder skill, create staging models, design mart models, implement tests, configure documentation

Example 2: Data quality testing

"Add comprehensive tests to dbt models" → Delegate to test-generator skill, implement schema tests, create data quality tests, configure freshness checks

Example 3: Incremental model

"Create incremental dbt model for large dataset" → Delegate to model-builder skill, design incremental strategy, implement merge logic, add tests

Read the full file on GitHub · 76 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 · 76 lines · 37 tokens per session scan A 0fda923896e6

Subscribe to this mod's changes

dbt-architect is an agent published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 490 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 2026-08-30.