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 warehouse-performancegit 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/warehouse-performance)<a href="https://agentmods.dev/skills/sdebruyn/fabric-dw-mcp-cli/warehouse-performance"><img src="https://agentmods.dev/badge/skills/sdebruyn/fabric-dw-mcp-cli/warehouse-performance/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/sdebruyn/fabric-dw-mcp-cli/warehouse-performance"><img src="https://agentmods.dev/badge/skills/sdebruyn/fabric-dw-mcp-cli/warehouse-performance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00138 | $0.02796 |
| Opus 5 | $0.00069 | $0.01398 |
| Sonnet 5 | $0.00028 | $0.00559 |
| Haiku 4.5 | $0.00014 | $0.00280 |
Grade A, and why
warehouse-performance 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warehouse-Wide Performance Investigation & Tuning
Investigates the performance of an entire Fabric Data Warehouse using the fabric-dw CLI and MCP tools, then proposes (and optionally applies) tuning actions. This is the warehouse-wide counterpart to query-optimizer, which diagnoses a single query.
Inputs
Gather these from the user (via $ARGUMENTS or natural language) before starting:
- workspace: workspace name or GUID
- warehouse: warehouse name or GUID. May be a Fabric Data Warehouse (DWH) or a SQL Analytics Endpoint; some steps are DWH-only (noted per step)
- window (optional): a time range for the query-hotspot views (
--since/--until, ISO-8601)
The CLI binary is fdw (also installed as fabric-dw). All MCP tool names below are exposed by the fabric-dw MCP server.
Read-only steps (1–4 reads) are safe to run unprompted. Every mutating action (step 3 toggle, step 4 create/update/delete/enable/disable) is gated behind explicit user confirmation; see Guardrails.
When NOT to use this skill
If the user wants to diagnose or rewrite ONE specific query (execution plan, statistics on that query's tables, or clustering), hand off to /query-optimizer. This skill stops at warehouse-wide hotspots and emits each query's query_hash so the user can feed a specific query to query-optimizer.
Workflow
Step 1 - Find query hotspots (DWH + SQL Analytics Endpoint)
Identify the warehouse's most expensive and most frequent workloads. These views read Query Insights and work on both DWH and SQL Analytics Endpoints.
fdw queries long-running <workspace>/<warehouse> --limit 20 # server-ordered by median elapsed time DESC
fdw queries frequent <workspace>/<warehouse> --limit 20 # server-ordered by run count DESC
fdw sql-pools insights <workspace>/<warehouse> # resource-pressure events (beta/preview, see step 4)
MCP equivalents: list_long_running_queries, list_frequent_queries, list_sql_pool_insights.
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.
- 8d ago First seen · 163 lines · 138 tokens per session scan A f5698561a237
warehouse-performance is a skill published in the GitHub repository sdebruyn/fabric-dw-mcp-cli (10 stars, last pushed 2d ago), licensed MIT. It adds 138 tokens to every session and 2,796 once invoked, about $0.0007 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
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.
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.
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.
sql-query-optimization
Diagnoses and optimises slow SQL queries using EXPLAIN ANALYZE. Covers identifying bottlenecks (sequential scans, bad estimates, heap fetches), index strategy, query rewrites, and verification. Invoked when the user asks to optimize a query, fix a slow database query, or improve database performance.
bitable
Access Lark Bitable databases - list tables, view fields, and read records. Use when user asks about a Bitable, database, or wants to query structured data.
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".