database-reviewer

database-reviewer is an agent for Claude Code from majiayu000/vibeguard. It costs 23 tokens per session (354 once invoked), scanned A, original, MIT.

A review agent for database code, SQL queries, database changes, and object-relational mapper (ORM) usage. An ORM lets application code work with database records through programming-language objects.

In plain words
What is it for?
It helps review query parameterization, indexes, N+1 queries, paging, reversible migrations, transactions, concurrency controls, connection pools, and timeouts.
Why use it?
It checks for security flaws, slow queries, unsafe changes, inconsistent data handling, and connection-management problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It helps review query parameterization, indexes, N+1 queries, paging, reversible migrations, transactions, concurrency controls, connection pools, and timeouts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/majiayu000/vibeguard/database-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/majiayu000/vibeguard

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 database-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/majiayu000/vibeguard/database-reviewer.svg)](https://agentmods.dev/agents/majiayu000/vibeguard/database-reviewer)
Your own site
<a href="https://agentmods.dev/agents/majiayu000/vibeguard/database-reviewer"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/database-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 354 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 $0.00023 $0.00354
Opus 5 $0.00012 $0.00177
Sonnet 5 $0.00005 $0.00071
Haiku 4.5 $0.00002 $0.00035

Measured 8d ago against content hash 38b4e073d912, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

database-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 8d 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.

agents/database-reviewer.md · 47 lines

What it actually says

Database Reviewer Agent

Responsibilities

Review database-related code to ensure data security, performance and consistency.

Review Checklist

Query security

  • SQL query parameterization (anti-injection)
  • Do not concatenate user input into SQL string
  • ORM queries do not use raw SQL (unless necessary and parameterized)

Query performance

  • No N+1 query (single query within loop → batch query)
  • Large table queries have index support
  • SELECT specified fields, do not use SELECT *
  • Paging query uses cursor-based instead of offset

Migration security

  • Migration scripts can be rolled back
  • ALTER for large tables without locking the table (using online DDL)
  • Data migration has backup strategy

Data consistency

  • Transaction boundaries are correct (related operations are within the same transaction)
  • Concurrent writing has optimistic locking or pessimistic locking
  • Multiple entries access the same data source with the same path (U-11)

Connection management

  • Use connection pooling
  • The connection is released correctly (defer close / context manager)
  • Timeout settings are reasonable

VibeGuard Constraints

  • Database paths are not hardcoded (U-11)
  • Multiple entry shared data source paths must be unified (U-11~U-14)
  • Don’t invent ORM APIs that don’t exist (L4)
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. 8d ago First seen · 47 lines · 23 tokens per session scan A 38b4e073d912

Subscribe to this mod's changes

database-reviewer is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 354 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.

Related

Other agents, from other repositories