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 sdebruyn/fabric-dw-mcp-cli --skill dbt-setupgit 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/skills/sdebruyn/fabric-dw-mcp-cli/dbt-setup)<a href="https://agentmods.dev/skills/sdebruyn/fabric-dw-mcp-cli/dbt-setup"><img src="https://agentmods.dev/badge/skills/sdebruyn/fabric-dw-mcp-cli/dbt-setup.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.01048 |
| Opus 5 | $0.00057 | $0.00524 |
| Sonnet 5 | $0.00023 | $0.00210 |
| Haiku 4.5 | $0.00012 | $0.00105 |
Grade A, and why
dbt-setup 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt Project Bootstrap for Fabric DW
Generates a complete dbt-fabric project scaffold using the fabric-dw MCP tools and writes all files to the local filesystem.
Inputs
Gather these from the user (via $ARGUMENTS or natural language) before starting:
- workspace: workspace name or GUID
- warehouse: Fabric Data Warehouse name or GUID
- project_name: desired dbt project name (default: warehouse name, lowercased, spaces replaced with underscores)
- schema: default dbt schema (default:
dbo) - authentication:
default(DefaultAzureCredential),sp(service principal), orinteractive(default:default) - with_sources: whether to generate a column-rich
_sources.yml(default:true, recommended)
Workflow
Step 1 - Resolve the warehouse connection
Call get_warehouse with the workspace and warehouse name. This returns the warehouse metadata including the connection string used in the dbt profile.
Step 2 - Confirm connectivity and list objects
Call list_schemas and list_tables to confirm that the warehouse is reachable and to identify the schemas and tables that will appear as dbt sources.
Show the user a summary: number of schemas found, number of tables found.
Step 3 - Generate the dbt scaffold
Call generate_dbt_profile with:
workspace,warehouse,project_name,schema,authenticationas providedwith_sources=true(unless the user explicitly opted out)
When with_sources=true, the tool performs a bulk column fetch and emits a models/staging/_sources.yml that already includes each table's columns: block with name and formatted data_type for every column. This output is ready for dbt contract enforcement and column-level documentation without any manual assembly.
Step 4 - Write files to the local filesystem
Write all file contents returned by generate_dbt_profile to the user's working directory. The expected set of files:
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.
- 7d ago First seen · 89 lines · 115 tokens per session scan A 8270d91cbaad
dbt-setup is a skill published in the GitHub repository sdebruyn/fabric-dw-mcp-cli (10 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 1,048 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
nosql-database-design
Designs a NoSQL data model by leading with access pattern analysis. Covers DynamoDB single-table design (PK/SK/GSI) and MongoDB embedding vs referencing, consistency models, and capacity planning. Invoked when the user asks to design a DynamoDB schema, MongoDB data model, or NoSQL data model.
json-to-toon
Transforms JSON input into Token-Oriented Object Notation (TOON) to reduce token consumption in LLM prompts and context windows. Applies the full TOON spec: inline primitive arrays, tabular format for uniform object arrays, and list format for heterogeneous or nested structures. Invoked when the user asks to compress…
relational-database-design
Designs or reviews a relational database schema for a given domain. Covers table structure, normalization, indexes, constraints, and migration strategy. Invoked when the user asks to design a schema, review a database structure, or optimize a data model.
video-prompt-engineer
Write and fix prompts for AI video generation.
hotin
Use when asked what is new, trending, hot, or worth using in AI right now - which repos, models, papers or launches matter this week, or whether a specific project is gaining traction. Answers from a ranked board with evidence instead of from training data or search-engine marketing.