A workflow for reviewing SQL queries and database change scripts. SQL is the language used to read and change database data; migration scripts modify database structure or data over time.

Reviewing SQL queries, table or schema changes, and data migrations for injection risks, performance, indexing, rollback safety, and effects on related Hibernate mappings.

It checks for security risks, slow queries, missing indexes, unsafe changes, data loss, locking problems, rollback issues, and compatibility concerns.

How zexion7873/copilot-setting configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zexion7873/copilot-setting. 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/zexion7873/copilot-setting/main/.github/skills/sql-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zexion7873/copilot-setting

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zexion7873/copilot-setting/sql-review/github.svg)](https://agentmods.dev/skills/zexion7873/copilot-setting/sql-review)

Your own site

<a href="https://agentmods.dev/skills/zexion7873/copilot-setting/sql-review"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/sql-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zexion7873/copilot-setting/sql-review"><img src="https://agentmods.dev/badge/skills/zexion7873/copilot-setting/sql-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,323 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.01323
Opus 5.5	$0.00044	$0.00529
Sonnet 5.5	$0.00022	$0.00265
Haiku 4.5	$0.00011	$0.00132

Measured 1mo ago against content hash 6b99e1807bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sql-review 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 1mo 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.

.github/skills/sql-review/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQL Review — Workflow

SQL-focused review covering both queries and schema migrations. Rules: instructions/sql.instructions.md (queries) + instructions/sql-ddl.instructions.md (migrations).

Phase 0 — Load canonical rules

MANDATORY pre-load gate — do NOT report findings (Phase 7) until you have opened the instruction files for the SQL under review. Your training data defaults to modern Java/Spring; these files are the version lock for Java 8 / Spring 3.2 / Hibernate 4.2. Open them first, every time — the negative lists in the agent body are a floor, not the full rules. Read-back receipt: NAME each file you opened and QUOTE its single most load-bearing rule for this change — a generic restatement you could have written from memory means you skipped the file.

SQL under review — open each one: instructions/sql.instructions.md, instructions/sql-ddl.instructions.md, instructions/spring-hibernate.instructions.md (hbm.xml mappings to re-align after a schema change), instructions/xml-config.instructions.md (hbm.xml structure / conventions).

Phase 1 — Collect and Classify

Find all SQL in scope: raw JDBC, HQL, native queries, stored procedures, dynamic query construction, and migration scripts (DDL / data-modifying DML).

Route each statement:

Queries (SELECT / application-level DML) → Phases 2–3
Migrations (CREATE / ALTER / DROP, backfill UPDATE / DELETE / INSERT SELECT) → Phases 4–6. Classify target table size (small <100k rows, medium 100k–10M, large >10M). Ask if unknown. Note migration ordering and inter-statement dependencies.

Skip the phases of the track that has no statements in scope.

Phase 2 — Check Query Security

Parameters bound via ? or :named — never concatenated
LIKE wildcards sanitized
No sensitive columns in SELECT *

Phase 3 — Check Query Performance

Only needed columns selected
WHERE/JOIN columns likely indexed
No functions on indexed columns
Large result sets paginated (cursor, not OFFSET)
No N+1 pattern (SQL inside loop)

Read the full file on GitHub · 102 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.

1mo ago Changed · -5 lines 6b99e1807bcd
2mo ago First seen · 107 lines · 110 tokens per session scan A bc9f740d22a8

Subscribe to this mod's changes

sql-review is a skill published in the GitHub repository zexion7873/copilot-setting (1 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,323 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

Code review Databases Java ai-agents copilot-instructions github-copilot hibernate prompt-engineering

sql-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sql-reviewzexion7873/copilot-setting	Skill	1	1mo ago	MIT	A	110	Claude Code, Codex
code-reviewgithub/awesome-copilot	Skill	41k	yesterday	MIT	A	27	Claude Code, Codex
code-review-csharppnp/copilot-prompts	Skill	902	3d ago	MIT	A	66	Claude Code, Codex
mcp-server-reviewpnp/copilot-prompts	Skill	902	3d ago	MIT	A	93	Claude Code, Codex
dataverse-fetchxml-builderpnp/copilot-prompts	Skill	902	3d ago	MIT	A	54	Claude Code, Codex
814-regulations-iso-25010jabrena/plinth	Skill	460	yesterday	Apache-2.0	A	83	Claude Code, Codex
059-design-atddjabrena/plinth	Skill	460	yesterday	Apache-2.0	A	93	Claude Code, Codex

copilot-setting: Skill for Claude Code