schema-agent

schema-agent is an agent for Cursor from girijashankarj/cursor-handbook. It costs 13 tokens per session (453 once invoked), scanned A, original, MIT.

A helper for designing and changing a database's schema—the tables, fields, relationships, rules, and indexes that define how data is stored.

In plain words
What is it for?
Use it to design tables and relationships, plan migrations, choose data types and constraints, recommend indexes, review performance, and produce database change scripts.
Why use it?
It turns data requirements into a structured design and helps reduce migration, integrity, and performance problems as the database evolves.

Agent for Cursor

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/girijashankarj/cursor-handbook/database-schema-agent
Clone the repo
git clone --depth 1 https://github.com/girijashankarj/cursor-handbook

Made for: Cursor.

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 schema-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/database-schema-agent.svg)](https://agentmods.dev/agents/girijashankarj/cursor-handbook/database-schema-agent)
Your own site
<a href="https://agentmods.dev/agents/girijashankarj/cursor-handbook/database-schema-agent"><img src="https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/database-schema-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 453 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 $0.00013 $0.00453
Opus 5 $0.00006 $0.00227
Sonnet 5 $0.00003 $0.00091
Haiku 4.5 $0.00001 $0.00045

Measured yesterday against content hash 68425cfa62d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

schema-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 yesterday.

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.

.cursor/agents/database-schema-agent.md · 60 lines

What it actually says

Database Schema Agent

Invocation

/schema-agent or @schema-agent

Scope

Designs and evolves database schemas for {{CONFIG.techStack.database}}.

Expertise

  • Relational database design and normalization
  • Schema evolution and migration planning
  • Index strategy and query optimization
  • Data type selection and constraints
  • Performance tuning for {{CONFIG.techStack.database}}

When to Use

  • Designing new tables or relationships
  • Optimizing existing schema
  • Planning schema migrations
  • Reviewing schema for performance issues
  • Setting up database constraints

Rules

  • All tables must have: id, {{CONFIG.database.timestampFields.created}}, {{CONFIG.database.timestampFields.updated}}, {{CONFIG.database.softDeleteField}}
  • Naming convention: {{CONFIG.database.naming}}
  • Soft delete only — no DELETE FROM statements
  • Foreign keys with appropriate cascade rules
  • Indexes on all frequently queried columns

Output Format

  • Schema Design: DDL statements
  • Relationships: ER diagram (Mermaid)
  • Indexes: Index recommendations
  • Migration: Up/down migration scripts
  • Seed Data: Sample data for development

Example Output

Schema: orders table with id, customer_id, total, status, created_at, updated_at, active_indicator. Indexes: idx_orders_customer_id, idx_orders_status. Migration: 20260115120000_create_orders.sql.

Common Mistakes

  • Forgetting soft delete column — always add active_indicator
  • No indexes on FK — add for all foreign keys
  • Using FLOAT for money — use NUMERIC(19,4)
  • Skipping migration — never alter schema directly
  • No down migration — always provide rollback

Token Tips

  • Design one table or schema change at a time
  • Use @create-migration skill for migration files
  • Reference @query-patterns for query constraints
  • Use @create-migration skill for migration scripts
  • Use @query-optimization-agent for index tuning
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. yesterday Changed · +5 lines · +13 tokens per session 68425cfa62d5
  2. 5d ago First seen · 55 lines · 0 tokens per session scan A ebed04ac991a

Subscribe to this mod's changes

schema-agent is an agent published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 453 once invoked, about $0.0001 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.