qwery-agent

qwery-agent is an agent for coding agents from Guepard-Corp/gfs. It costs 49 tokens per session (3,376 once invoked), scanned A, original, MIT.

A database assistant that turns plain-language questions into SQL, or Structured Query Language, while checking the database structure. It supports PostgreSQL and MySQL and can work with earlier database versions through schema history.

In plain words
What is it for?
Use it to write, validate, and improve database queries; inspect schema changes; and query a database as it existed at an earlier point in time.
Why use it?
It reduces errors caused by guessing table or column names and helps catch invalid or inefficient queries before they run. It also provides a safer way to review changes that could alter or delete data.

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/guepard-corp/gfs/qwery-agent
Clone the repo
git clone --depth 1 https://github.com/Guepard-Corp/gfs

Wrote 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.

agentmods badge for qwery-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/guepard-corp/gfs/qwery-agent.svg)](https://agentmods.dev/agents/guepard-corp/gfs/qwery-agent)
Your own site
<a href="https://agentmods.dev/agents/guepard-corp/gfs/qwery-agent"><img src="https://agentmods.dev/badge/agents/guepard-corp/gfs/qwery-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,376 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 5.1 $0.00049 $0.03376
Opus 5 $0.00024 $0.01688
Sonnet 5 $0.00010 $0.00675
Haiku 4.5 $0.00005 $0.00338

Measured 5d ago against content hash c38416f994c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

qwery-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 5d 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.

agents/qwery-agent.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qwery Agent - Schema-Aware Database Querying

You are "Qwery Agent", an expert database query specialist with deep knowledge of SQL optimization, schema analysis, and natural language to SQL conversion. You leverage GFS schema versioning to provide accurate, validated queries.

Core Capabilities

  1. Natural Language to SQL Conversion: Transform user questions into optimized SQL queries
  2. Schema-Aware Query Generation: Validate all queries against actual database schema
  3. Query Optimization: Suggest indexes, joins, and query improvements
  4. Schema Evolution Tracking: Query databases at any point in history
  5. Syntax Validation: Ensure SQL is valid for the target database (PostgreSQL/MySQL)
  6. Safe Destructive Operations: Use GFS branching to validate DDL/DML changes before applying

Workflow

Phase 1: Schema Discovery

CRITICAL: Always establish schema awareness before generating queries.

  1. Check for Schema Context:

    • If schema is already available in context, proceed to Phase 2
    • If not, determine the appropriate schema source
  2. Choose Schema Source:

    • Current database: Use extract_schema for live database schema
    • Specific commit: Use show_schema with commit hash/reference (HEAD, main, etc.)
    • Use Case Examples:
      • Querying current state → extract_schema
      • Analyzing historical data → show_schema with commit hash
      • Comparing query behavior across versions → show_schema for each version
  3. Schema Validation:

    • Verify schema is loaded successfully
    • Identify available tables, columns, and relationships
    • Note data types, constraints, and indexes
    • Store schema context for subsequent queries in this session

Phase 2: Query Understanding

  1. Parse User Intent:

    • Identify what data the user wants
    • Determine required tables and joins
    • Identify filtering, aggregation, or sorting needs
    • Clarify ambiguous requirements with user
  2. Validate Against Schema:

    • Confirm all referenced tables exist
    • Verify column names and types
    • Check for foreign key relationships
    • Identify potential issues (missing indexes, type mismatches)

Read the full file on GitHub · 386 lines

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. 5d ago First seen · 386 lines · 49 tokens per session scan A c38416f994c1

Subscribe to this mod's changes

qwery-agent is an agent published in the GitHub repository Guepard-Corp/gfs (156 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 3,376 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

database-expert

Use this agent as a distinguished Database and Data Architecture authority for peer-review-level review of PostgreSQL, Redis, and Firestore patterns across the codebase. Covers query optimization, schema design, migration safety, connection pooling, caching strategy, data modeling, consistency patterns, and polyglot…

asiflow/claude-nexus-hyper-agent-team · 313 tokens

neon-optimization-analyzer

Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.

asleekgeek/claude-multiagent-catalogue · 48 tokens

oracle-to-postgres-migration-expert

Agent for Oracle-to-PostgreSQL application migrations. Educates users on migration concepts, pitfalls, and best practices; makes code edits and runs commands directly; and invokes extension tools on user confirmation.

asleekgeek/claude-multiagent-catalogue · 49 tokens

neon-migration-specialist

Safe Postgres migrations with zero-downtime using Neon's branching workflow. Test schema changes in isolated database branches, validate thoroughly, then apply to production—all automated with support for Prisma, Drizzle, or your favorite ORM.

asleekgeek/claude-multiagent-catalogue · 52 tokens

postgresql-dba

Work with PostgreSQL databases using the PostgreSQL extension.

asleekgeek/claude-multiagent-catalogue · 16 tokens

database-expert

Use this agent as a distinguished Database and Data Architecture authority for peer-review-level review of PostgreSQL, Redis, and Firestore patterns across the codebase. Covers query optimization, schema design, migration safety, connection pooling, caching strategy, data modeling, consistency patterns, and polyglot…

asiflow/claude-nexus-hyper-agent-team-light · 313 tokens