sql_query_agent

An agent that writes, examines, and improves SQL queries, which are instructions for retrieving data from databases. It works with one data product that you provide.

In plain words
What is it for?
Use it to turn a plain-language data request into SQL, analyze or optimize a query, and provide guidance for running it.
Why use it?
It avoids searching for a data source when you already know which one to use, keeping the query work focused on that source.

Agent

Install

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.

agentmods
npx agentmods add agents/alation/alation-ai-agent-sdk/sql_query_agent
Clone the repo
git clone --depth 1 https://github.com/Alation/alation-ai-agent-sdk
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 180 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00180
Opus 5 $0.00000 $0.00090
Sonnet 5 $0.00000 $0.00036
Haiku 4.5 $0.00000 $0.00018

Measured 2d ago against content hash 059f57817588, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sql_query_agent 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.

guides/agents/sql_query_agent.md · 21 lines

What it actually says

sql_query_agent

SQL Query Agent for SQL query generation and analysis.

Functionality

This agent specializes in generating, analyzing, and optimizing SQL queries based on natural language descriptions of data needs. It differs from the Query Flow Agent in that it must be provided a data product. It will not look for data products to query.
This is useful if the caller already knows which data product to query and wants an agent which will deterministically query that data product only.

Input Parameters

  • message (required, str): Description of the data you need or SQL task
  • data_product_id (required, str): Which data product to use.
  • chat_id (optional, uuid): An existing chat to use. If not provided, a new chat will be created.

Returns

  • SQL queries, query analysis, optimization suggestions, and execution guidance.
Changes

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.

  1. 2d ago First seen · 21 lines · 0 tokens per session scan A 059f57817588

Subscribe to this mod's changes

sql_query_agent is an agent published in the GitHub repository Alation/alation-ai-agent-sdk (19 stars, last pushed 28d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 180 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 2026-08-30.