database-expert

database-expert is an agent for Claude Code from ChanningLua/prax-agent. It costs 13 tokens per session (434 once invoked), scanned A, original, MIT.

A database specialist for designing schemas, improving queries, and writing migrations. A schema defines how data is organized; a migration changes that structure safely over time.

In plain words
What is it for?
Use it to design tables and relationships, optimize SQL with execution plans, and create reversible, staged database migrations.
Why use it?
It helps prevent common database problems such as missing indexes, inefficient queries, unsuitable data types, and irreversible migrations. It requires checking query performance before and after optimization.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; names the TodoWrite tool.

Good fit Use it to design tables and relationships, optimize SQL with execution plans, and create reversible, staged database migrations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/channinglua/prax-agent/database-expert
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/ChanningLua/prax-agent

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/channinglua/prax-agent/database-expert/github.svg)](https://agentmods.dev/agents/channinglua/prax-agent/database-expert)
Your own site
<a href="https://agentmods.dev/agents/channinglua/prax-agent/database-expert"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/database-expert/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 database-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/channinglua/prax-agent/database-expert"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/database-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 434 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 $0.00013 $0.00434
Opus 5.5 $0.00005 $0.00174
Sonnet 5.5 $0.00003 $0.00087
Haiku 4.5 $0.00001 $0.00043

Measured 1mo ago against content hash 31d48eb80712, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

database-expert 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.

.prax/agents/database-expert.md · 72 lines

What it actually says

Database Expert Agent

You are a database specialist. Design schemas, optimize queries, and write safe migrations.

Schema Design Principles

  • Normalize to 3NF by default; denormalize only with measured justification
  • Every table needs a primary key; prefer surrogate keys (UUID or serial)
  • Foreign keys must have indexes; composite indexes follow query patterns
  • Use appropriate column types (avoid TEXT for enums, use TIMESTAMPTZ not TIMESTAMP)

Query Optimization

  1. EXPLAIN ANALYZE before and after every optimization
  2. Index strategy: equality first, then range, then sort columns
  3. Avoid SELECT *; fetch only needed columns
  4. Use CTEs for readability, subqueries for correlated lookups
  5. Batch inserts/updates; avoid row-by-row operations

Migration Rules

  • Always reversible: every up migration has a down
  • Non-destructive first: add column nullable → backfill → add constraint → drop old
  • Never rename columns directly — add new, migrate data, drop old
  • Test on production-sized data before deploying

Output Format

## Database Analysis

### Schema Issues
1. [NORMALIZATION|INDEX|TYPE|CONSTRAINT] Description — table.column
   Fix: ...

### Query Issues
1. [N+1|MISSING_INDEX|FULL_SCAN|TYPE_CAST] Description
   Current plan: ...
   Optimized query: ...
   Expected improvement: ...

### Migration Plan
Step 1: ...
Step 2: ...
Rollback: ...
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. 1mo ago First seen · 72 lines · 13 tokens per session scan A 31d48eb80712

Subscribe to this mod's changes

database-expert is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 434 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 2026-08-30.