validate-dbt

A command for checking a dbt project, where dbt is a tool that builds and tests data models from SQL. It checks the project setup, compiles models, runs tests, and reviews documentation.

In plain words
What is it for?
Use it to validate one model or an entire project, check compilation and tests, find missing descriptions or tests, and suggest improvements.
Why use it?
It finds configuration, SQL, test, and documentation problems before they affect data users.

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/armanzeroeight/fastagent-plugins/validate-dbt
Clone the repo
git clone --depth 1 https://github.com/armanzeroeight/fastagent-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00010 $0.00408
Opus 5 $0.00005 $0.00204
Sonnet 5 $0.00002 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 2d ago against content hash d61708683534, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-dbt 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/commands/validate-dbt.md · 81 lines

What it actually says

Validate dbt Project

Context

  • dbt version: !dbt --version 2>&1 || echo "dbt not installed"
  • Current directory: !pwd
  • dbt project: !ls dbt_project.yml 2>&1 && echo "Found" || echo "Not in dbt project"
  • Models: !find models -name "*.sql" 2>&1 | head -10 || echo "No models found"

Your Task

Validate dbt project configuration, compile models, and run tests.

Arguments

  • $1: Model name to validate (optional, validates all if not provided)

Steps

  1. Validate project configuration

    dbt debug
    
  2. Compile models

    dbt compile --select $1
    
  3. Run tests

    dbt test --select $1
    
  4. Check documentation

    • Verify all models have descriptions
    • Check column documentation
    • Ensure tests are defined
  5. Provide recommendations

    • Missing tests
    • Undocumented models
    • Performance improvements
    • Best practice violations

Output Format

## dbt Validation Results

**Project:** [project-name]
**Models Checked:** [count]

### Configuration
✓ Passed / ✗ Failed

### Compilation
✓ Passed / ✗ Failed
[Compilation errors if any]

### Tests
✓ Passed / ✗ Failed
- Total: [count]
- Passed: [count]
- Failed: [count]

### Documentation Coverage
- Models documented: [count]/[total]
- Columns documented: [count]/[total]

### Recommendations
1. [Recommendation]
2. [Recommendation]
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 · 81 lines · 10 tokens per session scan A d61708683534

Subscribe to this mod's changes

validate-dbt is a command published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 408 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.