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/sqlgit clone --depth 1 https://github.com/sdebruyn/fabric-dw-mcp-cliWhat 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 | $0.00000 | $0.03747 |
| Opus 5 | $0.00000 | $0.01873 |
| Sonnet 5 | $0.00000 | $0.00749 |
| Haiku 4.5 | $0.00000 | $0.00375 |
Grade A, and why
sql 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 2d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running SQL
SQL execution and query-plan capture against a Fabric Data Warehouse or SQL Analytics Endpoint.
Targets: Data Warehouse / SQL Analytics Endpoint
CLI
sql exec
Execute a SQL statement or file against a warehouse or SQL Analytics Endpoint. Provide the query via -q/--query or -f/--file (not both). Multi-statement batches are supported; the CLI keeps the last result set that has a column list (i.e. the last query), not the last statement. A batch that ends with DDL/DML after a query, such as SELECT id FROM t; UPDATE t SET x = 1;, shows the SELECT result and does not separately report that the UPDATE ran. A statement with no result set at all (DDL/DML with nothing else in the batch) returns empty columns and rows.
!!! warning
This command executes arbitrary SQL, including DDL and DML. Ensure you have the correct target before running destructive statements.
Synopsis
fdw [-w WORKSPACE] sql exec [OPTIONS] [ITEM]
| Option | Description |
|---|---|
-q / --query TEXT |
SQL statement or batch to execute inline. |
-f / --file PATH |
Path to a .sql file to execute. UTF-8 and UTF-8 BOM files are both supported. |
--watch SECONDS |
Re-execute and redraw every positive number of seconds. Cannot be combined with --json. |
Output defaults to a Rich table (rows/columns). Pass --json on the root command to emit machine-readable JSON ({"columns": [...], "rows": [...], "rowcount": N}).
Whether a Query executed successfully. rowcount=N message or a table is shown depends on the returned result set (see above), not on whether it has any rows. A SELECT that matches nothing still returns its column list, so it renders as a table with headers and a (0 rows) line underneath; the rowcount=N message only appears when no result set with columns was returned at all. When the columns are too wide to fit the terminal, the empty table is replaced by a wrapped Columns: ... list, still followed by (0 rows), so the column names stay readable instead of being truncated inside a table cell.
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.
- 2d ago First seen · 277 lines · 0 tokens per session scan A 4b3e9ce7a084
sql 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 3,747 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
next-feature
You MUST complete ALL steps below in a single run — selecting the feature, building it, validating, updating features.json, committing, and printing the summary. Do NOT stop, pause, or ask for input between steps. The job is not done until the final summary is printed.
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
validate-dependencies
Validate all task dependencies for issues.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).