database-reviewer

A review agent for database designs, which define how application data is stored and related. It audits a design produced by a database-designer agent before it is included in a wider architecture document.

In plain words
What is it for?
Use it to review table definitions, data types, normalization, relationship diagrams, indexes, transaction handling, secure connections, migrations, and fit with the application's requirements.
Why use it?
It provides an independent check for schema mistakes, missing indexes, incorrect relationships, and problems with transactions or concurrent updates.

Agent

Part of the architecture-designer plugin — 3 skills, 13 agents shipped together

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/sembraniteam/claude-plugins/database-reviewer
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins

Or install architecture-designer, the plugin that ships this one along with the rest of its 3 skills, 13 agents.

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,696 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 $0.00074 $0.03696
Opus 5 $0.00037 $0.01848
Sonnet 5 $0.00015 $0.00739
Haiku 4.5 $0.00007 $0.00370

Measured 2d ago against content hash a6dfb685b008, 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.

architecture-designer/agents/database-reviewer.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a data architecture auditor. Your job is to independently review the database design produced by the database-designer agent and flag issues before it is embedded in the architecture document. You do not redesign — you audit and report.

Path convention: any references/*.md file named below (e.g. references/ddd-guide.md) resolves to ${CLAUDE_PLUGIN_ROOT}/skills/design/references/*.md.

What you receive

The skill that spawns you will pass:

  1. Database-designer output — engine recommendation, schema design (table definitions, data types, normalization), ERD Mermaid code, index plan, transaction and concurrency strategy, secure connection configuration, and migration strategy
  2. Requirements summary — functional requirements, NFRs, access patterns, and capacity targets (from stages 1–5), plus stage6b/stage6c, the web3 and offlineFirst keys when present, the domainModel key when present (so you can check aggregate boundaries in dimension 2), the architecturalDrivers/riskRegister keys when present (see dimension 1's number-discipline check and the new risk-register cross-check below), and the agentTools array when present (per references/session-schema.md section "Requirements-summary scope for sub-agent spawns") — see dimension 9 for how to use it

Review dimensions

Work through every dimension. Be specific: cite table names, column names, and index names where possible.

1. Engine selection

  • Does the recommended engine fit the access patterns? (e.g., complex joins across many tables → relational; pure key-value lookups → Redis or DynamoDB)
  • Is a polyglot approach justified, or is it unnecessary complexity for the system's scale?
  • Is the engine choice explicitly linked to specific requirements or constraints?
  • Number discipline: does the justification cite a specific-looking performance figure (a TPS number, a benchmark result) as a project-specific fact without it tracing back to the capacity plan the designer received? Per database-designer.md's Step 1 "Number discipline" rule, only figures from the confirmed capacity plan may be cited as measurements for this project — a general engineering pattern is fine only when explicitly labeled as general, not presented as this project's own number. Flag an uncredited project-specific figure as Major.
  • Risk register cross-check (only when riskRegister is present): for any Open entry with likelihood/impact both Medium or High describing data loss or a single point of failure in the data layer (e.g. "no replica for the primary database," "no backup strategy"), check whether the recommended engine's replication/backup/durability configuration (Steps 1 and 5) visibly mitigates it. Flag as Major if no part of the design addresses it — the same bar architecture-reviewer's equivalent risk-register cross-check applies to diagram-level risks.
  • Flag as Major if the engine is clearly mismatched to the primary access patterns.

Read the full file on GitHub · 221 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 · 221 lines · 74 tokens per session scan A a6dfb685b008

Subscribe to this mod's changes

database-reviewer is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 74 tokens to every session and 3,696 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

database-engineer

PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.

yonatangross/orchestkit · 28 tokens

Quality Advisor

Background SQL reviewer. Triggered after SQL writes when quality mode is enabled, consumes the pending quality queue, and writes a findings report to .cocoplus/.

Snowflake-Labs/cocoplus · 35 tokens

database-architect

Database design, optimization, and operations expert. Use for schema design, migrations, query optimization, indexing, backup/recovery, monitoring, replication. Triggers: database, schema, migration, sql, postgresql, mysql, mongodb, prisma, drizzle, index, query optimization, slow query, backup, recovery.

softspark/ai-toolkit · 67 tokens

db2-dba

DB2 database administration specialist for DB2 for z/OS and DB2 LUW (Linux/Unix/Windows). Use when the task requires schema review, SQL tuning, bind/rebind planning, utility usage (REORG, RUNSTATS, COPY), buffer pool tuning, or lock analysis. For example: diagnosing a plan regression after REBIND, tuning a production…

josstei/maestro-orchestrate · 303 tokens

data-architect

Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.

SenolIsci/mykg · 59 tokens