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 commands/sdebruyn/fabric-dw-mcp-cli/dbtgit clone --depth 1 https://github.com/sdebruyn/fabric-dw-mcp-cliWrote 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/commands/sdebruyn/fabric-dw-mcp-cli/dbt)<a href="https://agentmods.dev/commands/sdebruyn/fabric-dw-mcp-cli/dbt"><img src="https://agentmods.dev/badge/commands/sdebruyn/fabric-dw-mcp-cli/dbt.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 | $0.00000 | $0.01543 |
| Opus 5 | $0.00000 | $0.00772 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00154 |
Grade A, and why
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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt
Scaffold a dbt project pre-wired to a Microsoft Fabric Data Warehouse using the dbt-fabric adapter.
No dbt installation is required to run these commands - fabric-dw generates all project files itself. A requirements.txt inside the scaffolded project lists the required pip packages (dbt-core, dbt-fabric) so you can install them in a separate environment when you are ready to run dbt.
Targets: Data Warehouse
CLI
dbt init
Targets: Data Warehouse
Scaffold a new dbt project directory connected to a Fabric Data Warehouse. The command creates the folder, writes dbt_project.yml, profiles.yml, requirements.txt, .gitignore, standard dbt model directories, a sample model, and a README. If git is on your PATH and the target folder is not already a git repository, git init is run automatically.
!!! warning "Security"
When `--auth sp` (Service Principal) is used, `profiles.yml` emits Jinja2 `env_var()` placeholders (`{{ env_var('AZURE_TENANT_ID') }}` etc.) instead of literal secrets. You must set `AZURE_TENANT_ID`, `AZURE_CLIENT_ID`, and `AZURE_CLIENT_SECRET` in your environment before running dbt.
Usage
fdw [-w WORKSPACE] dbt init [OPTIONS] [ITEM] FOLDER
Arguments
| Argument | Description |
|---|---|
ITEM |
Name or ID of the Fabric Data Warehouse item (optional if set via fdw config set warehouse). |
FOLDER |
Path to the folder to create. Must not exist (unless --force is passed). |
Options
| Option | Default | Description |
|---|---|---|
--project-name TEXT |
derived from ITEM name |
dbt project name (sanitised: lowercase, non-alphanumeric chars replaced with _). |
--profile-name TEXT |
same as --project-name |
dbt profile name written into profiles.yml and dbt_project.yml. |
--schema TEXT |
dbo |
Default target schema for dbt models. |
--target TEXT |
dev |
dbt target name inside the profile. |
--threads INTEGER RANGE |
4 |
Number of dbt threads (1–64). |
--auth [auto|CLI|ServicePrincipal|interactive|sp] |
derived from active credential mode | Authentication method. interactive is an alias for CLI; sp is an alias for ServicePrincipal. |
--profiles-dir [project|home] |
project |
Where to write profiles.yml. project writes it next to dbt_project.yml; home merges it into ~/.dbt/profiles.yml (backs up existing file first). |
--with-sources |
off | Introspect the live warehouse and generate a _sources.yml file listing all schemas and tables. |
--force |
off | Overwrite an existing non-empty directory. |
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 · 125 lines · 0 tokens per session scan A 11079f71542a
dbt is a command published in the GitHub repository sdebruyn/fabric-dw-mcp-cli (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,543 tokens. 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 2026-08-31.
Other commands, from other repositories
ingest
Manually add knowledge to the Weaviate store.
dejavu-weaviate-rescue
Weaviate corruption rescue toolkit — scan, quarantine-segment, redo-class. Codifies the 2026-05-14 LSM-segment rescue playbook.
optimize-doctrine
Optimisation Requêtes Doctrine.
web-ingest
Crawl the configured source and generate knowledge markdown files.
web-update
Re-ingest a URL or refresh a local knowledge file, then rebuild the search index.
data
Invoke the Data Engineer for ETL/ELT, dbt, warehouses, streaming, orchestration, and data quality.