multi-tenant

multi-tenant is a command for Claude Code from luanpdd/kit-mcp. It costs 56 tokens per session (2,470 once invoked), scanned A, original, MIT.

A coordinator for building business-to-business SaaS applications where multiple organizations share one system but their data stays separated.

In plain words
What is it for?
Use it to plan or implement tenant isolation, member invitations, onboarding, administrator features, audit logs, and Supabase database or server functions.
Why use it?
It brings related work such as organization setup, permissions, audit logs, and database row-level security into one workflow.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Good fit Use it to plan or implement tenant isolation, member invitations, onboarding, administrator features, audit logs, and Supabase database or server functions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/multi-tenant
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/luanpdd/kit-mcp

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 multi-tenant

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/multi-tenant.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/multi-tenant)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/multi-tenant"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/multi-tenant.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,470 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 $0.00056 $0.02470
Opus 5 $0.00028 $0.01235
Sonnet 5 $0.00011 $0.00494
Haiku 4.5 $0.00006 $0.00247

Measured 4d ago against content hash 1c76de293e11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

multi-tenant 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 4d 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/commands/multi-tenant.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Suite Invocation Pattern (introduzido v1.21): Agents da Suíte Multi-Tenant delegam para agents da Suíte Supabase v1.8 quando precisam materializar SQL, Edge Functions, RLS policies, Realtime, Storage. Padrão canônico:

  • b2b-saas-architect → delega plano de migration para supabase-migration-writer
  • multi-tenant-rls-writer → herda anti-pitfalls de supabase-rls-writer via cross-ref
  • evolution-go-integrator → delega Edge Function code para supabase-edge-fn-writer
  • audit-log-implementer → usa skill supabase-cron-queues para retention scheduling
  • org-onboarding-implementer → invoca supabase-migration-writer para migration + supabase-edge-fn-writer para wizard

Cria/Atualiza: o que cada agent invocado cria/atualiza (skills consultadas, migrations propostas, Edge Functions, agents implementers).

Após: o usuário tem o output do agent (plano, código, SQL, ou veredito de auditoria).

<execution_context> Skills consultadas pelos agents: kit/skills/{b2b-saas-architecture,multi-tenant-rls-hierarchy,rbac-permissions-matrix-supabase,multi-tenant-performance-scaling,org-onboarding-flow,member-invite-flow,super-admin-platform-pattern,audit-log-multi-tenant,lgpd-multi-tenant-compliance,evolution-go-whatsapp-integration,whatsapp-conversation-state-machine,crm-lead-pipeline-patterns,org-switcher-react-pattern,permission-gate-react-pattern,member-management-react-shadcn}/SKILL.md + kit/skills/_shared-multi-tenant/glossary.md + cross-ref ATIVO para kit/skills/_shared-supabase/glossary.md.

Agents disponíveis (Suíte Multi-Tenant v1.21): kit/agents/{b2b-saas-architect,multi-tenant-rls-writer,multi-tenant-isolation-auditor,lgpd-compliance-auditor,org-onboarding-implementer,invite-flow-implementer,super-admin-implementer,audit-log-implementer,evolution-go-integrator,crm-pipeline-implementer}.md.

Agents Suíte Supabase v1.8 invocados via cross-suite delegation: supabase-architect, supabase-migration-writer, supabase-rls-writer, supabase-edge-fn-writer, supabase-realtime-implementer, supabase-storage-implementer, supabase-auth-bootstrapper. </execution_context>

Subcomandos suportados (sinônimos PT-BR/EN):

Subcomando Sinônimos Agent dispatched
arquiteto architect, arch b2b-saas-architect
rls-tenant rls, policies multi-tenant-rls-writer
isolation-audit audit-tenancy, auditar-tenancy multi-tenant-isolation-auditor
lgpd-audit lgpd, compliance, compliance-audit lgpd-compliance-auditor
onboarding org, onboard org-onboarding-implementer
convite invite, invitation invite-flow-implementer
super-admin admin, platform-admin super-admin-implementer
audit-log audit, auditoria-log audit-log-implementer
whatsapp evolution-go, wpp, evolution evolution-go-integrator
crm pipeline, crm-pipeline, leads crm-pipeline-implementer
help ajuda, ? exibe esta tabela inline

Aliases globais para o nome da suíte: multi-tenant, b2b, tenant, escritorio, tenancy (todos roteiam para este orquestrador via /multi-tenant).

Detect supabase/config.toml: se presente, extrai project_id e passa como contexto para o agent (mesmo pattern de /supabase v1.8).

1. Parsear Subcomando

SUBCMD=$(echo "$ARGUMENTS" | awk '{print $1}')
ARGS=$(echo "$ARGUMENTS" | cut -d' ' -f2-)

Se $ARGUMENTS for vazio ou SUBCMD for help/ajuda/?: exibir tabela de subcomandos inline + exemplo de uso. Sair.

Read the full file on GitHub · 164 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. 4d ago First seen · 164 lines · 56 tokens per session scan A 1c76de293e11

Subscribe to this mod's changes

multi-tenant is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 2,470 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.