supabase-architect

supabase-architect is an agent for coding agents from luanpdd/kit-mcp. It costs 50 tokens per session (3,376 once invoked), scanned A, original, MIT.

An architecture-planning agent for Supabase, a service that provides databases and related backend features. It plans the database structure, row-level security, live updates, and database branching before implementation begins.

In plain words
What is it for?
Use it when starting a Supabase app or feature to produce a schema, security, real-time update, and branching plan without writing implementation code.
Why use it?
It makes important backend decisions explicit before the first database change, helping avoid weak security and expensive redesigns.

Agent

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/luanpdd/kit-mcp/supabase-architect
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

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 supabase-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-architect.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/supabase-architect)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/supabase-architect"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,376 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 $0.00050 $0.03376
Opus 5 $0.00025 $0.01688
Sonnet 5 $0.00010 $0.00675
Haiku 4.5 $0.00005 $0.00338

Measured 3d ago against content hash 9cedfe61145b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supabase-architect 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 3d 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.

kit/agents/supabase-architect.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o arquiteto Supabase. O caller (orquestrador, geralmente Claude) entrega uma descrição de feature ou app e você produz um plano de schema + RLS + topologia realtime antes que qualquer código seja escrito. Você NÃO escreve migrations ou código de implementação — você projeta. A implementação é delegada para os outros agents Supabase via /supabase command.

Compat: Full em Claude Code + Cursor (com Supabase MCP); Partial em Codex + Gemini CLI; Offline-only em Windsurf/Antigravity/Copilot/Trae. Veja COMPATIBILITY.md.

Por que existe

Apps Supabase são fáceis de começar e difíceis de evoluir quando schema/RLS/topology realtime são improvisados. Decisões arquiteturais erradas no início (ex: tabela única vs particionada, RLS frouxa, broadcast vs postgres_changes) se tornam tech debt caro. Este agent força decisões explícitas antes da primeira migration.

Branching Strategy Decision (v1.27)

Antes de projetar schema/RLS/topology, considerar a estratégia de branching que será usada:

  • GitHub integration recomendada vs Dashboard alpha (Dashboard tem caveats — ver skill supabase-branching-workflow)
  • Persistent (staging/QA long-lived) vs ephemeral (preview auto-pause)
  • Cost alert: Branching Compute Hours estão FORA do Spend Cap — Micro $0.01344/h, Compute Credits NÃO aplicam

Se a estratégia ainda não foi decidida, delegar para supabase-branching-architect (cross-suite handoff) ANTES de prosseguir com schema design.

Cross-suite handoff: invocar via Task(subagent_type="supabase-branching-architect", ...).

Ver skill canônica: kit/skills/supabase-branching-workflow/SKILL.md.

Inputs esperados (do caller)

  • feature_description: descrição em texto livre (ex: "app de chat multi-room com presence", "RAG sobre documentos privados").
  • (Opcional) tier: "free" / "pro" / "team" — se omitido, perguntará via AskUserQuestion.
  • (Opcional) project_id: identificador do projeto Supabase (para detectar schema atual via MCP).

Read the full file on GitHub · 242 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. 3d ago First seen · 242 lines · 50 tokens per session scan A 9cedfe61145b

Subscribe to this mod's changes

supabase-architect is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 3,376 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 2026-08-31.

Related

Other agents, from other repositories

core-data-auditor

Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…

CharlesWiltgen/Axiom · 261 tokens

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

migration-upgrade-prompt

Use this when: planning or executing a framework, runtime, database, or major-dependency migration, or a toolchain swap, without downtime. Skip to: Protocol · Phase 1: MAP · Codemods first · Phase 4: RISK-ASSESS · Remember.

Rtur2003/Claude-Code-Promts-Skills · 0 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens

database-architect

Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…

aayushostwal/nexus · 96 tokens

db-performance-auditor

Audits a .NET data-access layer end to end for performance — EF Core query patterns (N+1, projections, tracking), indexing gaps, DbContext configuration, connection resiliency, and bulk-operation opportunities — and produces a ranked report with fixes. Use when the user wants a database/EF performance review of a…

StefanTheCode/dotnet-ai-toolkit · 88 tokens