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.
npx skills add AltimateAI/data-engineering-skills --skill testing-dbt-modelsgit clone --depth 1 https://github.com/AltimateAI/data-engineering-skillsWrote 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.
[](https://agentmods.dev/skills/altimateai/data-engineering-skills/testing-dbt-models)<a href="https://agentmods.dev/skills/altimateai/data-engineering-skills/testing-dbt-models"><img src="https://agentmods.dev/badge/skills/altimateai/data-engineering-skills/testing-dbt-models/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.
<a href="https://agentmods.dev/skills/altimateai/data-engineering-skills/testing-dbt-models"><img src="https://agentmods.dev/badge/skills/altimateai/data-engineering-skills/testing-dbt-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 167 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01096 |
| Opus 5.5 | $0.00044 | $0.00438 |
| Sonnet 5.5 | $0.00022 | $0.00219 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade A, and why
testing-dbt-models 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- testing-dbt-models — 86% identical, 77 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt Testing
Every model deserves at least one test. Primary keys need unique + not_null.
Workflow
1. Study Existing Test Patterns
CRITICAL: Match the project's existing testing style before adding new tests.
# Find all schema.yml files with tests
find . -name "schema.yml" -exec grep -l "tests:" {} \;
# Read existing tests to learn patterns
cat models/staging/schema.yml | head -100
cat models/marts/schema.yml | head -100
# Check for custom tests or dbt packages
ls tests/
cat packages.yml 2>/dev/null
Extract from existing tests:
- YAML formatting style (indentation, spacing)
- Test coverage depth (all columns vs key columns only)
- Use of custom tests (dbt_utils, dbt_expectations, custom macros)
- Description style (brief vs detailed)
- Severity levels used (warn vs error)
2. Read Model SQL
cat models/<path>/<model_name>.sql
Identify: primary keys, foreign keys, categorical columns, date columns, business-critical fields.
3. Check Existing Tests for This Model
cat models/<path>/schema.yml | grep -A 50 "<model_name>"
# or
find . -name "schema.yml" -exec grep -l "<model_name>" {} \;
4. Identify Testable Columns
| Column Type | Recommended Tests |
|---|---|
| Primary key | unique, not_null |
| Foreign key | not_null, relationships |
| Categorical | accepted_values (ask user for valid values) |
| Required field | not_null |
| Date/timestamp | not_null |
| Boolean | accepted_values: [true, false] |
5. Write Tests in schema.yml
Match the existing style from step 1. Example format (adapt to project):
version: 2
models:
- name: model_name
description: "Brief description of what this model contains"
columns:
- name: primary_key_column
description: "Unique identifier for this record"
tests:
- unique
- not_null
- name: foreign_key_column
description: "Reference to related_model"
tests:
- not_null
- relationships:
to: ref('related_model')
field: related_key_column
- name: status
description: "Current status of the record"
tests:
- not_null
- accepted_values:
values: ['pending', 'active', 'completed', 'cancelled']
- name: created_at
description: "Timestamp when record was created"
tests:
- not_null
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.
- 1mo ago First seen · 175 lines · 110 tokens per session scan A ed76fbbbc317
testing-dbt-models is a skill published in the GitHub repository AltimateAI/data-engineering-skills (129 stars, last pushed 5d ago), licensed MIT. It adds 110 tokens to every session and 1,096 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…
test-sqrl
Use when adding or updating tests for a DataSQRL pipeline. Use after implementing features to verify correctness.
16-ai-llm-security
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.
eval-code
Write deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness…
eval-llm-judge
Write LLM-as-judge evaluator prompts for AI products. Use this skill whenever you need to evaluate semantic properties of AI outputs that cannot be checked programmatically — output quality, tone, factual accuracy, edge case handling, reference alignment. Also use when auditing existing judge prompts for bias…
pr-verify
Verify a Docglow change actually works before submitting or merging a PR. Runs the conformance suite, then a behavioral verification pass (flag matrix, artifact-join spot checks, pipeline contract sweep, payload budget). Use when reviewing a PR, self-reviewing a branch before opening a PR, or when asked to "verify…