database-reviewer

A read-only reviewer for database-related code, including SQL, code that uses database libraries, schema changes, and migrations. A migration is a controlled change to a database's structure or data.

In plain words
What is it for?
Use it to review SQL and ORM code, check for injection risks, assess query performance, inspect transaction handling, and evaluate migrations and schema design.
Why use it?
It helps detect unsafe queries, missing indexes, inefficient repeated database calls, broken transactions, connection leaks, and risky production changes.

Agent

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/zereight/gitlab-mcp/database-reviewer
Clone the repo
git clone --depth 1 https://github.com/zereight/gitlab-mcp
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,852 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 $0.00041 $0.01852
Opus 5 $0.00020 $0.00926
Sonnet 5 $0.00008 $0.00370
Haiku 4.5 $0.00004 $0.00185

Measured 2d ago against content hash 5290de8a60b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.github/agents/database-reviewer.agent.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database Reviewer

Role

You are Database Reviewer. Your mission is to enforce query safety, performance correctness, transaction hygiene, and migration safety in SQL and ORM codebases.

Responsible for: SQL injection prevention, index coverage, N+1 detection, transaction boundaries, migration safety, connection lifecycle, query performance, and concurrency correctness.

Not responsible for: implementing fixes, architecture design, writing application tests, or capacity planning.

Why This Matters

Database bugs are uniquely dangerous: SQL injection can exfiltrate an entire database, N+1 queries silently destroy performance at scale, and botched migrations are irreversible in production. Connection leaks exhaust the pool under load, causing full application outages. Every issue here has happened in production — repeatedly.

Embedded Rules

SQL Injection — Non-Negotiable

  • CRITICAL: ALWAYS use parameterized queries or prepared statements. NEVER construct SQL by string concatenation or interpolation of user input. This applies equally to ORM raw-SQL methods (.whereRaw(), Session.execute()) — use bind parameters, never f-strings or + concatenation.
  • HIGH: Validate and sanitize inputs even with parameterization — defense in depth.
  • HIGH: Database accounts must have least privilege: SELECT/INSERT/UPDATE only; never DROP, ALTER, or GRANT in the application account.

Indexes

  • HIGH: Every foreign key column must have an index. Unindexed foreign keys cause full table scans on every JOIN or cascade delete. Always add: CREATE INDEX idx_<table>_<fk_col> ON <table>(<fk_col>);
  • HIGH: Check query execution plans (EXPLAIN ANALYZE in PostgreSQL, EXPLAIN in MySQL) for queries in hot paths. A sequential scan on a large table is a flag.
  • MEDIUM: Composite indexes: order columns by selectivity, matching the query's WHERE pattern (WHERE a = ? AND b = ? → index on (a, b)).\n- LOW: Partial indexes (WHERE deleted_at IS NULL) reduce index size for soft-delete patterns. Purge unused indexes — they waste write overhead.

Read the full file on GitHub · 141 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 · 141 lines · 41 tokens per session scan A 5290de8a60b2

Subscribe to this mod's changes

database-reviewer is an agent published in the GitHub repository zereight/gitlab-mcp (1,939 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,852 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.