475-sql

A set of database-independent rules for writing and reviewing SQL, the language used to query and change databases. It covers reads, data changes, schema changes, permissions, transactions, and safeguards for risky operations.

In plain words
What is it for?
It helps analysts and engineers write queries, inspect affected rows before updates or deletes, use transactions for risky changes, and choose appropriate permissions and rollback practices.
Why use it?
It helps prevent accidental data loss and makes database changes easier to review, test, and roll back.

Cursor rule

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 rules/d-padmanabhan/agent-engineering-handbook/475-sql
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,055 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 $0.00033 $0.01055
Opus 5 $0.00016 $0.00528
Sonnet 5 $0.00007 $0.00211
Haiku 4.5 $0.00003 $0.00105

Measured 2d ago against content hash 2ef50fb8f429, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

475-sql 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.

rules/475-sql.mdc · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQL Engineering Ruleset

Audience: analysts and engineers writing or reviewing SQL (any RDBMS) Goal: write SQL that is safe-by-default, reviewable, and operationally predictable

[!IMPORTANT] This rule is intentionally database-agnostic. For PostgreSQL specifics, also follow 470-postgresql.mdc.

[!NOTE] For data-platform specifics, also see 480-data-engineering.mdc and the platform rules (481-databricks.mdc, 482-snowflake.mdc, 483-kafka.mdc, 484-teradata.mdc).


SQL command categories (mental model)

Use these categories to quickly understand risk, required privileges, and rollback strategy.

DQL - Data Query Language (read-only queries)

  • Primary command: SELECT
  • Common clauses: FROM, WHERE, GROUP BY, HAVING, ORDER BY, LIMIT, OFFSET

DML - Data Manipulation Language (changes table contents)

  • INSERT, UPDATE, DELETE, MERGE (where supported)

[!CAUTION] DML is where “I destroyed production data” incidents happen. Always prove the rowset first and use transactions for risky changes.

DDL - Data Definition Language (changes schema/objects)

  • CREATE, ALTER, DROP, TRUNCATE, RENAME

[!WARNING] DDL can take locks, block traffic, and be irreversible (especially DROP and TRUNCATE). Treat DDL as code: migration-reviewed, tested, and rolled out safely.

DCL - Data Control Language (permissions)

  • GRANT, REVOKE (and role/user management depending on DB)

TCL - Transaction Control Language (atomicity and recovery)

  • BEGIN / START TRANSACTION, COMMIT, ROLLBACK, SAVEPOINT

Destructive-operation guardrails (must follow)

DELETE / UPDATE safety

  • Never run DELETE or UPDATE without a WHERE.
  • Before destructive writes:
    • run the exact SELECT first to validate the target rows
    • record expected row count and a small sample of primary keys
  • Prefer patterns that make review safer:
    • ... WHERE ... RETURNING ... (when supported)
    • limit scope by immutable IDs, not names

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 33 tokens per session scan A 2ef50fb8f429

Subscribe to this mod's changes

475-sql is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (15 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,055 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.