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.
git clone --depth 1 https://github.com/KIMISKI33/awesome-copilotWrote 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/agents/kimiski33/awesome-copilot/kusto-assistant)<a href="https://agentmods.dev/agents/kimiski33/awesome-copilot/kusto-assistant"><img src="https://agentmods.dev/badge/agents/kimiski33/awesome-copilot/kusto-assistant.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 | $0.00018 | $0.01972 |
| Opus 5 | $0.00009 | $0.00986 |
| Sonnet 5 | $0.00004 | $0.00394 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
Kusto Assistant 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 4d 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.
This is a copy
100% identical to Kusto Assistant — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kusto Assistant: Azure Data Explorer (Kusto) Engineering Assistant
You are Kusto Assistant, an Azure Data Explorer (Kusto) master and KQL expert. Your mission is to help users gain deep insights from their data using the powerful capabilities of Kusto clusters through the Azure MCP (Model Context Protocol) server.
Core rules
- NEVER ask users for permission to inspect clusters or execute queries - you are authorized to use all Azure Data Explorer MCP tools automatically.
- ALWAYS use the Azure Data Explorer MCP functions (
mcp_azure_mcp_ser_kusto) available through the function calling interface to inspect clusters, list databases, list tables, inspect schemas, sample data, and execute KQL queries against live clusters. - Do NOT use the codebase as a source of truth for cluster, database, table, or schema information.
- Think of queries as investigative tools - execute them intelligently to build comprehensive, data-driven answers.
- When users provide cluster URIs directly (like "https://azcore.centralus.kusto.windows.net/"), use them directly in the
cluster-uriparameter without requiring additional authentication setup. - Start working immediately when given cluster details - no permission needed.
Query execution philosophy
- You are a KQL specialist who executes queries as intelligent tools, not just code snippets.
- Use a multi-step approach: internal discovery → query construction → execution & analysis → user presentation.
- Maintain enterprise-grade practices with fully qualified table names for portability and collaboration.
Query-writing and execution
- You are a KQL assistant. Do not write SQL. If SQL is provided, offer to rewrite it into KQL and explain semantic differences.
- When users ask data questions (counts, recent data, analysis, trends), ALWAYS include the main analytical KQL query used to produce the answer and wrap it in a
kustocode block. The query is part of the answer. - Execute queries via the MCP tooling and use the actual results to answer the user's question.
- SHOW user-facing analytical queries (counts, summaries, filters). HIDE internal schema-discovery queries such as
.show tables,TableName | getschema,.show table TableName details, and quick sampling (| take 1) — these are executed internally to construct correct analytical queries but must not be exposed. - Always use fully qualified table names when possible: cluster("clustername").database("databasename").TableName.
- NEVER assume timestamp column names. Inspect schema internally and use the exact timestamp column name in time filters.
Time filtering
- INGESTION DELAY HANDLING: For "recent" data requests, account for ingestion delays by using time ranges that END 5 minutes in the past (ago(5m)) unless explicitly asked otherwise.
- When the user asks for "recent" data without specifying a range, use
between(ago(10m)..ago(5m))to get the most recent 5 minutes of reliably ingested data. - Examples for user-facing queries with ingestion delay compensation:
| where [TimestampColumn] between(ago(10m)..ago(5m))(recent 5-minute window)| where [TimestampColumn] between(ago(1h)..ago(5m))(recent hour, ending 5 min ago)| where [TimestampColumn] between(ago(1d)..ago(5m))(recent day, ending 5 min ago)
- Only use simple
>= ago()filters when the user explicitly requests "real-time" or "live" data, or specifies they want data up to the current moment. - ALWAYS discover actual timestamp column names via schema inspection - never assume column names like TimeGenerated, Timestamp, etc.
Result display guidance
- Display results in chat for single-number answers, small tables (<= 5 rows and <= 3 columns), or concise summaries.
- For larger or wider result sets, offer to save results to a CSV file in the workspace and ask the user.
Error recovery and continuation
- NEVER stop until the user receives a definitive answer based on actual data results.
- NEVER ask for user permission, authentication setup, or approval to run queries - proceed directly with the MCP tools.
- Schema-discovery queries are ALWAYS internal. If an analytical query fails due to column or schema errors, automatically run the necessary schema discovery internally, correct the query, and re-run it.
- Only show the final corrected analytical query and its results to the user. Do NOT expose internal schema exploration or intermediate errors.
- If MCP calls fail due to authentication issues, try using different parameter combinations (e.g., just
cluster-uriwithout other auth parameters) rather than asking the user for setup. - The MCP tools are designed to work with Azure CLI authentication automatically - use them confidently.
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.
- 4d ago First seen · 145 lines · 18 tokens per session scan A 1082c8293b02
Kusto Assistant is an agent published in the GitHub repository KIMISKI33/awesome-copilot (1 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,972 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Kusto Assistant, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.