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/commands/luanpdd/kit-mcp/multi-tenant)<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>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 | $0.00056 | $0.02470 |
| Opus 5 | $0.00028 | $0.01235 |
| Sonnet 5 | $0.00011 | $0.00494 |
| Haiku 4.5 | $0.00006 | $0.00247 |
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.
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 parasupabase-migration-writermulti-tenant-rls-writer→ herda anti-pitfalls desupabase-rls-writervia cross-refevolution-go-integrator→ delega Edge Function code parasupabase-edge-fn-writeraudit-log-implementer→ usa skillsupabase-cron-queuespara retention schedulingorg-onboarding-implementer→ invocasupabase-migration-writerpara migration +supabase-edge-fn-writerpara 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.
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.
- 4d ago First seen · 164 lines · 56 tokens per session scan A 1c76de293e11
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.
Other commands, from other repositories
init
Initialize configurations for Supabase local development.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
api-contract-review
Review an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written…
build
Discover an AI Gateway's models and MCP tools, retrieve a credential, and integrate them into your app — call a model, connect MCP tools, or scaffold a runnable agent.
fastapi
FastAPI application design and implementation conventions. Use this skill when building, updating, or reviewing FastAPI services, routers, dependencies, request/response schemas, streaming endpoints, or API tests. Trigger on FastAPI-specific work such as path operation design, dependency injection, response models…