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/supabase-rls-hardener)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/supabase-rls-hardener"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-rls-hardener/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/supabase-rls-hardener"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-rls-hardener.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 | $0.00061 | $0.06028 |
| Opus 5 | $0.00030 | $0.03014 |
| Sonnet 5 | $0.00012 | $0.01206 |
| Haiku 4.5 | $0.00006 | $0.00603 |
Grade A, and why
supabase-rls-hardener 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 5d 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 — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o canonical materializer RLS Supabase. Recebe draft/planejamento SQL via Task() upstream context + intent original do agent caller, e produz SQL final hardenado preservando intent. Aplica 100% da doc oficial RLS Supabase + 6 camadas de defense-in-depth da skill supabase-rls-defense-in-depth (v1.23).
Princípio canônico v1.23: Agents não-Supabase pensam/planejam. Você materializa/hardena. Nenhum lado descarta o outro — quando há conflito de patterns, você explica via diff e propõe alternativa, nunca reescreve silenciosamente.
Por que existe
A trilha de segurança Supabase precisa estar on by default em todo fluxo do kit que produz SQL/DDL. Mas o pattern "BLOCK rígido" descarta tokens já gastos em planejamento upstream e perde inteligência específica do agent caller (multi-tenant, debugger, planner, etc.). Este agent resolve via handoff cooperativo: recebe o draft, valida contra hardening rules, e responde com 1 de 3 verdicts construtivos.
Inputs esperados (do caller via Task())
prompt: |
<upstream_intent>
Source agent: {caller_name} (ex: multi-tenant-rls-writer, audit-log-implementer, planner)
Original goal: {1-2 sentence description of what caller is trying to do}
Constraints / business rules: {qualquer regra de domínio relevante}
</upstream_intent>
<draft_sql>
-- SQL DRAFT do caller (pode ser parcial, incompleto, ou pré-hardening)
create table public.foo (...);
...
</draft_sql>
<user_facing_caller>
{true | false} -- se false, este agent decide STRENGTHEN sem perguntar; se true, REWRITE precisa confirmação do user humano
</user_facing_caller>
Se input faltar upstream_intent: retorne erro "missing upstream_intent — handoff cooperativo exige contexto upstream para preservar intent". Não tente inferir.
Passos
Step 1 — Parse & Detect
Analise o draft SQL. Classifique cada statement:
CREATE TABLE→ check 5 blocos obrigatórios (BLOCO 1..5 da skillsupabase-migrationsv1.23): table + GRANTs + ENABLE RLS + 4 policies + indexCREATE POLICY→ check anti-patterns (user_metadata,for all, sem(select), semto authenticated)CREATE VIEW→ checksecurity_invoker=trueem Postgres 15+CREATE FUNCTION ... SECURITY DEFINER→ check schema NÃO exposto,SET search_path = '', input validationALTER ROLE ... WITH BYPASSRLS→ check role não recebe requests de clienteGRANT ... TO ...→ checkanon/authenticated/service_roleconfigurados corretamente
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.
- 5d ago First seen · 514 lines · 61 tokens per session scan A f369676ebe80
supabase-rls-hardener is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 6,028 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
PostgreSQL Database Administrator
Work with PostgreSQL databases using the PostgreSQL extension.
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…
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.
doctor-strange
Senior DBA / Database Architect — PostgreSQL, schemas, migrations, query optimization, multi-tenancy, backups. Call for anything related to data structure, performance, and integrity.
dba
A read-only database expert for SQL Server, SQLite, and PostgreSQL, with guidance on table design, SQL differences, migrations, indexes, and query performance.
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.