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 agentmods add skills/altimateai/data-engineering-skills/documenting-dbt-modelsnpx skills add AltimateAI/data-engineering-skills --skill documenting-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/documenting-dbt-models)<a href="https://agentmods.dev/skills/altimateai/data-engineering-skills/documenting-dbt-models"><img src="https://agentmods.dev/badge/skills/altimateai/data-engineering-skills/documenting-dbt-models.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00105 | $0.01046 |
| Opus 5 | $0.00053 | $0.00523 |
| Sonnet 5 | $0.00021 | $0.00209 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
documenting-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt Documentation
Document the WHY, not just the WHAT. Include grain, business rules, and caveats.
Workflow
1. Study Existing Documentation Patterns
CRITICAL: Match the project's documentation style before adding new docs.
# Find all schema.yml files with documentation
find . -name "schema.yml" | head -5
# Read well-documented models to learn patterns
cat models/marts/schema.yml | head -150
cat models/staging/schema.yml | head -150
Extract from existing documentation:
- Description length (brief vs detailed)
- Formatting style (plain text vs markdown with headers)
- Information included (grain? business rules? caveats?)
- Column description depth (all columns vs key columns)
- Use of meta tags or custom properties
2. Read Model SQL
cat models/<path>/<model_name>.sql
Understand: transformations, business logic, joins, filters.
3. Check Existing Documentation for This Model
# Find existing schema.yml
find . -name "schema.yml" -exec grep -l "<model_name>" {} \;
# Read existing docs
cat models/<path>/schema.yml | grep -A 100 "<model_name>"
4. Identify Documentation Needs
For each model, document:
- Model description: Purpose, grain, key business rules
- Column descriptions: Business meaning, not just data type
For each column, consider:
- What business concept does this represent?
- Are there any caveats or special values?
- What is the source of this data?
5. Write Documentation
Match the style discovered in step 1. Example format (adapt to project):
version: 2
models:
- name: orders
description: |
Order transactions at the order line item grain.
Each row represents one product in one order.
**Business Rules:**
- Revenue recognized on ship_date, not order_date
- Cancelled orders excluded (status != 'cancelled')
- Returns processed as negative line items
**Grain:** One row per order_id + product_id combination
columns:
- name: order_id
description: |
Unique identifier for the order.
Source: orders.id from Stripe webhook
- name: customer_id
description: |
Foreign key to customers table.
NULL for guest checkouts (pre-2023 only)
- name: revenue
description: |
Net revenue for this line item in USD.
Calculation: unit_price * quantity - discount_amount
Excludes tax and shipping
- name: order_status
description: |
Current status of the order.
Values: pending, processing, shipped, delivered, cancelled, returned
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.
- 6d ago First seen · 168 lines · 105 tokens per session scan A 128a222b1c03
documenting-dbt-models is a skill published in the GitHub repository AltimateAI/data-engineering-skills (122 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,046 once invoked, about $0.0005 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.
Other skills, from other repositories
datahub-verified-remediation
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
Data Pipeline Architect
Design and implement robust data pipelines — ETL/ELT, streaming, batch processing. From architecture to code with Airflow, dbt, Kafka, and modern data stack.
ml-feature-engineering
Feature store patterns, training/serving skew prevention, feature pipelines for ML teams, point-in-time correct joins, and bridging data engineering with MLOps conventions. Use this skill whenever an ML team needs feature pipelines, when building a feature store or deciding whether to use one, when there's a…
python-data-patterns
Pandas, Polars, and PySpark idioms for production data engineering — chunked reads, memory-safe transforms, vectorized operations, type optimization, and performance patterns. Use this skill whenever the user is writing a Python data transformation script and running into memory issues, slow performance, or…
cloud-infra-data
AWS/GCP/Azure data infrastructure — S3/GCS/ADLS partitioning, BigQuery slot management, Redshift spectrum, Snowflake warehouses, IAM roles for data access, cost optimization, and managed service selection. Use this skill whenever the user is deploying a pipeline to cloud, choosing between managed data services…
orchestration-patterns
Airflow/Prefect/Dagster DAG design — task dependencies, retries, SLAs, backfill strategies, sensors, and failure recovery. Use this skill whenever the user is building or debugging a scheduled pipeline with multiple steps, asking how to handle task failures, setting up retries or alerts, designing a DAG structure…