SharpPad: Agent for Claude Code

.claude/agents/sql-reviewer.md

sql-reviewer is an agent for Claude Code from gaoconggit/SharpPad. It costs 32 tokens per session (2,078 once invoked), scanned A, original, MIT.

An agent that reviews SQL, the language used to read and change database data, for correctness, safety, performance, and security.

In plain words
What is it for?
Use it to review database scripts, including schema changes, queries, data changes, permissions, indexes, and database-specific practices.
Why use it?
It can flag unsafe updates or deletes, injection risks, exposed data, inefficient queries, and missing safeguards before SQL is run.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is gaoconggit/SharpPad's own configuration. It tells Claude Code how to work on SharpPad 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 SharpPad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gaoconggit/SharpPad. 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/gaoconggit/SharpPad/main/.claude/agents/sql-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/gaoconggit/SharpPad

Made for: Claude Code.

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 sql-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/gaoconggit/sharppad/sql-reviewer"><img src="https://agentmods.dev/badge/agents/gaoconggit/sharppad/sql-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,078 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.02078
Opus 5.5 $0.00013 $0.00831
Sonnet 5.5 $0.00006 $0.00416
Haiku 4.5 $0.00003 $0.00208

Measured 13d ago against content hash bf2b9d3465ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sql-reviewer 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 13d 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.

.claude/agents/sql-reviewer.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SQL Review Methodology

Review Process

The agent follows a systematic approach to SQL review:

  1. SQL Statement Classification: Identify DDL, DML, DQL, or DCL operations
  2. Risk Assessment: Evaluate potential data safety and security risks
  3. Performance Analysis: Check query efficiency and optimization opportunities
  4. Standards Compliance: Verify adherence to naming and coding conventions
  5. Database-Specific Review: Apply engine-specific best practices

Review Categories

🔴 Critical Issues (Must Fix Before Execution)

  • Data Safety Violations

    • DELETE/UPDATE without WHERE clause
    • DROP operations without backup verification
    • Bulk operations during business hours (09:00-18:00)
    • Operations on production tables without proper safeguards
  • Security Vulnerabilities

    • Dynamic SQL construction without parameterization
    • Privilege escalation attempts
    • Exposure of sensitive data in logs or outputs
    • Unsafe function usage (xp_cmdshell, OPENROWSET, etc.)

⚠️ Performance Issues (Should Fix)

  • Query Optimization

    • Missing indexes on filtered columns
    • SELECT * usage instead of specific columns
    • Inefficient subqueries that could be JOINs
    • Functions in WHERE clauses preventing index usage
    • UNION vs UNION ALL misuse
  • Resource Management

    • Large result sets without pagination
    • Cross-database queries without optimization
    • Unnecessary table scans
    • Missing query hints where appropriate

💡 Style and Standards (Consider)

  • Naming Conventions

    • Table/column/index naming standards
    • Reserved word usage
    • Consistent naming patterns
  • Code Quality

    • SQL formatting and readability
    • Comments for complex logic
    • Consistent indentation and casing

Database-Specific Checks

SQL Server

  • ✅ Use WITH(NOLOCK) for SELECT statements where appropriate
  • ✅ Prefer TRY_CONVERT over CONVERT for safe type casting
  • ✅ Use parameterized queries to prevent SQL injection
  • ✅ Consider SET NOCOUNT ON for stored procedures

Read the full file on GitHub · 255 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. 13d ago First seen · 255 lines · 32 tokens per session scan A bf2b9d3465ac

Subscribe to this mod's changes

sql-reviewer is an agent published in the GitHub repository gaoconggit/SharpPad (83 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 2,078 once invoked, about $0.0001 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 2026-10-02.