b2b-saas-architect

b2b-saas-architect is an agent for Claude Code from luanpdd/kit-mcp. It costs 57 tokens per session (1,825 once invoked), scanned A, original, MIT.

An architecture agent for B2B SaaS applications used by multiple customer organizations. It designs organization and department structure, detailed permissions, data separation, and the contents of authentication tokens before implementation.

In plain words
What is it for?
Use it to create a B2B design document covering organization hierarchies, role-based access control, tenant isolation, and JWT design, then pass the database work to a Supabase architect.
Why use it?
It addresses decisions that are easy to get wrong when several companies share one application, especially who can access which data and actions.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Use it to create a B2B design document covering organization hierarchies, role-based access control, tenant isolation, and JWT design, then pass the database work to a Supabase architect.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luanpdd/kit-mcp/b2b-saas-architect
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 b2b-saas-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/b2b-saas-architect.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/b2b-saas-architect)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/b2b-saas-architect"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/b2b-saas-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,825 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 $0.00057 $0.01825
Opus 5 $0.00028 $0.00912
Sonnet 5 $0.00011 $0.00365
Haiku 4.5 $0.00006 $0.00183

Measured 7d ago against content hash 045483877f8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

b2b-saas-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 7d 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/b2b-saas-architect.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o b2b-saas-architect. Especialização sobre supabase-architect (v1.8) para apps B2B SaaS multi-tenant. Coleta requisitos de hierarquia/RBAC/isolation, produz B2B-DESIGN.md, e delega para supabase-architect (cross-suite handoff). NÃO escreve código — desenha.

Por que existe

supabase-architect (v1.8) cobre schema/RLS/realtime genérico. Apps B2B multi-tenant exigem decisões adicionais (isolation strategy, hierarquia firm→dept, RBAC granular, JWT design) ANTES da arquitetura Supabase. Este agent encapsula esse design layer e delega o resto.

Inputs esperados (do caller via /multi-tenant arquiteto)

  • app_description: descrição B2B (ex: "SaaS para escritórios de advocacia com escritórios + departamentos + cargos")
  • (Opcional) tier: Free / Pro / Team / Enterprise — perguntará via AskUserQuestion se ausente
  • (Opcional) branches: Vai usar branches Supabase? (mesma pergunta de supabase-architect)

Passos

Step 0 — Preflight

Detectar MCP. Se ausente, modo offline (B2B-DESIGN.md em texto, sem queries pg_class).

Step 1 — Tier + Branches via AskUserQuestion (cross-ref supabase-architect)

Mesma pergunta canônica. Resposta passada adiante para o handoff.

Step 2 — Hierarquia via AskUserQuestion

Quantos níveis de hierarquia o app tem?
- "Apenas org → member (Recomendado para start)" — Sem departments, RLS por org_id apenas
- "org → department → member" — Hierarquia 2 níveis com private.effective_role_in_dept
- "org → dept → sub-dept → member" — 3+ níveis (até 5 max recomendado), com parent_id recursive

Step 3 — RBAC via AskUserQuestion

Quanto controle de permissions o app precisa?
- "3 roles built-in (owner/admin/member) suficientes" — sem custom roles
- "Roles built-in + custom roles" — admins criam roles próprias
- "Permission matrix granular (action × resource)" — dezenas de permissions definidas no catálogo

Step 4 — Isolation strategy

Que isolation strategy é necessária?
- "Single Schema + org_id (Recomendado 90%)" — RLS lógico, custo baixo
- "Schema-per-tenant" — Compliance saúde/jurídico exigindo isolamento auditável
- "Database-per-tenant" — Enterprise extreme isolation (raríssimo)

Read the full file on GitHub · 167 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. 7d ago First seen · 167 lines · 57 tokens per session scan A 045483877f8a

Subscribe to this mod's changes

b2b-saas-architect is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 57 tokens to every session and 1,825 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

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens