agentmods.dev

deepsql: Instructions file for Codex

AGENTS.md

deepsql AGENTS.md is an instructions file for Codex, OpenCode from DeepSQLAI/deepsql. It costs 5,352 tokens per session, scanned D, original, Apache-2.0.

Repository instructions for DeepSQL, a database performance assistant with a Java backend and React frontend. A monorepo is one repository containing multiple related parts of a project.

In plain words
What is it for?
They are for starting the backend and frontend, running backend tests and linting, and starting the PostgreSQL database used by the project.
Why use it?
They give agents a quick map of the codebase, supported databases, technologies, and commands for development and testing.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is DeepSQLAI/deepsql's own configuration. It tells Codex and OpenCode how to work on deepsql itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deepsql configures →

not rated 40repo 5d ago D scan 5,352 tokens original Apache-2.0
View source ↗ DeepSQLAI/deepsql deepsql.ai
Reuse

Borrowing it

Nothing to install: this file belongs to DeepSQLAI/deepsql. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DeepSQLAI/deepsql/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/DeepSQLAI/deepsql

Made for: Codex, OpenCode.

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 deepsql AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/deepsqlai/deepsql/agents-md/github.svg)](https://agentmods.dev/instructions/deepsqlai/deepsql/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/deepsqlai/deepsql/agents-md"><img src="https://agentmods.dev/badge/instructions/deepsqlai/deepsql/agents-md/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.

agentmods 80×15 button for deepsql AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/deepsqlai/deepsql/agents-md"><img src="https://agentmods.dev/badge/instructions/deepsqlai/deepsql/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,352 This file is loaded in full into every session.
When invoked 5,352 The same file — it is already loaded in full.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.05352 $0.05352
Opus 5.5 $0.02141 $0.02141
Sonnet 5.5 $0.01070 $0.01070
Haiku 4.5 $0.00535 $0.00535

Measured 2mo ago against content hash ec8247a1889a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

deepsql AGENTS.md scanned grade D with 3 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **PostgreSQL 16** (vault DB, port 5432): start with `sudo pg_ctlcluster 16 main start`.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

`curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash -s -- --non-interactive --skip-setup`,

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

VM so `curl http://127.0.0.1:3000` fails even though Vite looks healthy. Vite proxies
AGENTS.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Persistent, high-level understanding of this codebase for all AI agents (Codex, Claude, Cursor, Antigravity). For comprehensive details, see docs/root/CLAUDE.md. For development commands and key rules, see CLAUDE.md.

Project Overview

DBA Agent — AI-powered Database Performance Assistant with autonomous troubleshooting.

  • Monorepo: Java backend (backend/) + React frontend (src/)
  • Backend: Spring Boot 4.0.3 (Java 25), Spring AI 2.0.0-M2, PostgreSQL vault DB
  • Frontend: React 19.2.3, Vite 7.3.0, Tailwind CSS 4.1.18, Zustand, TanStack Query v5
  • AI: Azure OpenAI (gpt-5.4-pro, text-embedding-3-large), Azure AI Search (RAG)
  • Databases supported: PostgreSQL, MySQL (extensible via provider registry)

Commands

# Backend
cd backend && mvn spring-boot:run          # Start backend (localhost:8080)
cd backend && mvn test                      # Run tests (143 tests, ~31 min)

# Frontend
npm install && npm run dev                  # Start frontend (localhost:3000)
npm run lint                                # Lint

# Database
docker compose up -d postgres               # Start vault DB (PostgreSQL)

Backend Architecture (Java)

Entry point: backend/src/main/java/com/dbaagent/DbaAgentApplication.java

Package Map

Package Purpose
controller/ REST endpoints (25+ controllers)
service/ Core business logic
service/brain/ ML-based DB intelligence (workload, config, query, classification)
model/ JPA entities and domain models
repository/ Spring Data JPA repositories
provider/ Database dialect registry — PostgreSQL and MySQL providers
config/ Spring configuration beans
security/ JWT auth, RBAC (VIEWER/EDITOR/ADMIN)
util/ Shared utilities (SQL parsing, normalization)

Key Domains

  • Chat/RAG: SpringAIChatService → ChatClient with advisor chain (memory, feedback, schema, performance, RAG)
  • Connections: ConnectionService manages HikariCP pools per database, SSH tunneling via SshTunnelService
  • Slow Query: Ingestion (SlowLogIngestionService), parsing (SlowQueryLogParserService), fingerprinting (QueryFingerprintService), optimization (QueryOptimizationService)
  • Brain Intelligence: Workload characterization, knob identification, config tuning, cardinality estimation, plan pattern memoization
  • Schema Analysis: 8 classification services (access patterns, anti-patterns, health scores, business domains, data sensitivity, partition readiness, relationships, temporal)
  • Performance Actions: ROI-ranked recommendations from multiple sources (index advisor, slow query analysis, brain config, anti-patterns, key columns)
  • Playbooks: JSON-based automation with scheduled execution and multi-channel alerts
  • Monitoring: Growth anomaly detection, performance insights, schema change tracking

Read the full file on GitHub · 336 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. 2mo ago First seen · 336 lines · 5,352 tokens per session scan D ec8247a1889a

Subscribe to this mod's changes

deepsql AGENTS.md is an instructions file published in the GitHub repository DeepSQLAI/deepsql (40 stars, last pushed 5d ago), licensed Apache-2.0. It adds 5,352 tokens to every session, about $0.0214 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIsDatabasesFrontendLLMaidatabase-performancemcp-servermysql
Related

deepsql AGENTS.md compared with instructions from other repositories

deepsql AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deepsql AGENTS.mdDeepSQLAI/deepsqlInstructions file405d agoApache-2.0D5,352Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode