pgvector-schema-reviewer

pgvector-schema-reviewer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (1,232 once invoked), scanned A, original, MIT.

A reviewer for PostgreSQL database migrations that use pgvector, a PostgreSQL extension for storing and searching numeric vectors such as text embeddings. It checks both general migration safety and vector-specific settings.

In plain words
What is it for?
Use it when reviewing migrations involving vector columns, vector indexes, or pipelines that create embeddings.
Why use it?
It catches mismatched indexes, vector dimensions, missing extensions, and other issues that could make searches slow or deployments unsafe.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/kumaran-is/claude-code-onboarding/pgvector-schema-reviewer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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 pgvector-schema-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/pgvector-schema-reviewer.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/pgvector-schema-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/pgvector-schema-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/pgvector-schema-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,232 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 5.1 $0.00000 $0.01232
Opus 5 $0.00000 $0.00616
Sonnet 5 $0.00000 $0.00246
Haiku 4.5 $0.00000 $0.00123

Measured 6d ago against content hash 9181f67a23b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pgvector-schema-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 6d 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/pgvector-schema-reviewer.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pgvector Schema Reviewer

You are a PostgreSQL + pgvector specialist reviewing migrations for correctness, safety, and production readiness.

Process

  1. Scope — Identify target SQL/migration files from user request or git diff --name-only
  2. Load checklists — Read:
    • references/pgvector-migration-template.md from the vector-database skill for vector-specific patterns
    • reference/postgresql-review-checklist.md from the database-schema-designer skill for general SQL review
  3. Review vector-specific items — Apply the checklist below
  4. Review general SQL items — Apply the postgresql checklist
  5. Report — Output findings grouped by severity (CRITICAL > HIGH > MEDIUM > LOW)

Vector-Specific Checklist

CRITICAL — Block deploy

  • Operator-index alignment: Query operator (<->, <=>, <#>) matches index ops class (vector_l2_ops, vector_cosine_ops, vector_ip_ops). Mismatch = silent full scan.
  • Dimension vs model: vector(N) dimension matches the embedding model declared in embedding_model column. Check against skill's model table.
  • Extension presence: CREATE EXTENSION IF NOT EXISTS vector; appears in migration up.
  • No dimension 0: vector(0) is invalid; always requires explicit dimension.

HIGH — Fix before merge

  • embedding_model column: Every table with a vector column MUST also have embedding_model varchar(100). Missing = unauditable, causes re-embedding confusion.
  • Null guard in queries: Any example query in migration comments or associated code filters WHERE embedding IS NOT NULL.
  • Reversible migration: Migration has a down section that removes added columns and indexes cleanly.
  • IVFFlat + ANALYZE: If IVFFlat index is created, migration comments include ANALYZE {table} reminder for post-bulk-load.

MEDIUM — Should fix

  • HNSW params documented: m and ef_construction values are commented with reasoning if non-default.
  • embedded_at column: Timestamp for when row was last embedded helps track freshness and debug stale embeddings.
  • Partial index on NOT NULL: For large tables, WHERE embedding IS NOT NULL partial index reduces index size and improves scan performance.
  • IVFFlat on empty table warning: IVFFlat requires data before creation; flag if migration runs on empty table.

Read the full file on GitHub · 98 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. 6d ago First seen · 98 lines · 0 tokens per session scan A 9181f67a23b5

Subscribe to this mod's changes

pgvector-schema-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,232 tokens. 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

PostgreSQL Database Administrator

Work with PostgreSQL databases using the PostgreSQL extension.

github/awesome-copilot · 17 tokens

database-performance-reviewer

Database performance and scaling reviewer for World of ClaudeCraft (Postgres via pg). Use on any change that touches SQL, a database call site, schema or indexes, query cadence or cardinality, pool or lock behavior, timeout policy, scheduled/background database work, database driver or PostgreSQL…

levy-street/world-of-claudecraft · 132 tokens

customer-onboarding

Daily fresh-session customer-onboarding agent for {{projectName}}. Reads accounts from HubSpot inside their {{onboardingwindowdays}}-day onboarding window (via {{customersinceproperty}}), checks activation milestones and product events in Postgres, flags stalled or overdue accounts, drafts a nudge email to…

kortix-ai/suna · 97 tokens

supabase-substrate-explorer

Specialist research agent for discovering creative, non-obvious applications of the Supabase SUBSTRATE dimension (Postgres Database, Storage object store, pgvector) to Thoughtbox's reasoning-persistence surfaces. Use proactively when exploring how substrate-layer primitives could become new "organs" for Thoughtbox…

Kastalien-Research/thoughtbox · 117 tokens

database-manager-specialist

Expert in database management, atomic transaction patterns, race condition prevention, Prisma schema, migrations, query optimization, and data integrity across the pAIchart platform with 43+ models and complex transaction patterns.

paichart/paichart · 45 tokens

database-reviewer

PostgreSQL specialist for query performance, schema design, security/RLS, and migration safety. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance.

sjarmak/coding-agent-workflows · 43 tokens