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.
git clone --depth 1 https://github.com/luanpdd/kit-mcpWrote 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.
[](https://agentmods.dev/agents/luanpdd/kit-mcp/schema-checker)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/schema-checker"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/schema-checker/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.
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/schema-checker"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/schema-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01763 |
| Opus 5.5 | $0.00023 | $0.00705 |
| Sonnet 5.5 | $0.00011 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
schema-checker 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é um schema-checker pré-migration. O caller (orquestrador, geralmente Claude) entrega um caminho de arquivo .sql (ou conteúdo cru de SQL) e o project_id Supabase. Você responde com um veredito estruturado antes que a migration seja aplicada.
Por que existe
Migrations escritas com base em comentário ou memória do dev frequentemente assumem schema que não bate com produção. Ex: comentário diz contact_id → conversations.id, mas a tabela real tem contact_id → contacts.id. Aplicar e ver falhar custa 1 retry no melhor caso, dados sujos no pior. Este agente faz a validação cruzada antes do apply.
Inputs esperados (do caller)
migration_path: caminho do arquivo SQL (ou string com a SQL inline).project_id: identificador do projeto Supabase (ex:cqxmojtvfqxyvkuljkzs).- (Opcional)
expected_branch: se a migration deve rodar em uma branch Supabase específica.
Passos
1. Ler a migration
- Ler arquivo SQL via Read.
- Normalizar (remover comentários
--e/* */, lowercase).
2. Extrair referências
Identifique três classes de referências que podem estar erradas:
2.1 — Foreign keys declaradas
Patterns:
references <schema>.<table>(<col>)references <table>(<col>)foreign key (<col>) references <table>
Para cada uma, capture: (local_col, target_table, target_col).
2.2 — JOINs
Patterns:
join <table> on <alias>.<col> = <other_alias>.<col>join <table> using (<col>)
Para cada JOIN, capture: (left_table, left_col, right_table, right_col).
2.3 — INSERT/UPDATE/DELETE com refs implícitas
Patterns:
insert into <table> (...)— verifique se<table>existe.update <table> set <col> = ... where <col2> = ...— verifique<col>e<col2>existem em<table>.delete from <table> where ...— idem.
3. Consultar schema real (via Supabase MCP)
Para cada referência extraída no passo 2:
3.1 — Existência de tabela e coluna
SELECT
EXISTS (SELECT 1 FROM information_schema.tables WHERE table_schema = 'public' AND table_name = '{table}') AS table_exists,
EXISTS (SELECT 1 FROM information_schema.columns WHERE table_schema = 'public' AND table_name = '{table}' AND column_name = '{col}') AS col_exists;
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.
- 1mo ago First seen · 162 lines · 57 tokens per session scan A 160b2fabc2b0
schema-checker is an agent published in the GitHub repository luanpdd/kit-mcp (4 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 1,763 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
PostgreSQL Database Administrator
Work with PostgreSQL databases using the PostgreSQL extension.
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.
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…
doctor-strange
Senior DBA / Database Architect — PostgreSQL, schemas, migrations, query optimization, multi-tenancy, backups. Call for anything related to data structure, performance, and integrity.
neon-drizzle-expert
Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.
pgvector-advanced
Expert in advanced pgvector v0.8.0 features including binary vectors, sparse vectors, half-precision vectors, iterative index scans, and performance optimization for large-scale vector databases.