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/invite-flow-implementer)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/invite-flow-implementer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/invite-flow-implementer/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/invite-flow-implementer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/invite-flow-implementer.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 | $0.00050 | $0.02206 |
| Opus 5.5 | $0.00020 | $0.00882 |
| Sonnet 5.5 | $0.00010 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
invite-flow-implementer 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 1mo 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o invite-flow-implementer. Materializa fluxo completo de invite — tabela + RPCs + cron expiração + Edge Function de envio email. Lê skill member-invite-flow. Delega SQL para supabase-migration-writer e Edge Function para supabase-edge-fn-writer.
Compat: Full em Claude Code + Cursor (com Supabase MCP); Partial em Codex + Gemini CLI.
Inputs
- (Opcional)
email_provider:supabase(default — usa Supabase Auth Email API),resend,sendgrid,postmark - (Opcional)
ttl_days: default 7 - (Opcional)
bulk_limit_per_hour: default 50
Passos
Step 0 — Preflight
- MCP detection
- Validar Phase 106 (organizations, organization_members, roles existem)
- Validar Phase 109 (audit_logs + private.audit_log function existem)
Step 1 — Email provider via AskUserQuestion (se ausente)
- Supabase Auth Email (Recomendado para start) — usa supabase.auth.admin.inviteUserByEmail OU email customizado via service role
- Resend — moderno, simples, 3000 emails/mês free
- SendGrid — enterprise, alta entregabilidade
- Postmark — alta entregabilidade, focused em transactional
Step 2 — Migration brief para supabase-migration-writer
[Migration brief — invite-flow-implementer]
Artefatos:
1. Tabela public.org_invites (DDL completo da skill member-invite-flow)
- 3 indexes + 1 unique partial (pending duplicate prevention)
- 3 RLS policies (member view + insert with permission + super_admin bypass)
2. RPC public.create_invite(p_org_id, p_email, p_role_name) → returns token text
3. RPC public.accept_invite(p_token) → returns jsonb com status
4. pg_cron schedule 'expire-pending-invites' diário 01:00 UTC
Validações no INSERT:
- Email format check
- Role exists na org
- Permission members:invite via RLS
- Bulk rate limit: <bulk_limit_per_hour> invites/hora por org_id
Delegar.
Step 3 — Edge Function brief para supabase-edge-fn-writer
[Edge Function brief — invite-flow-implementer]
Function name: send-invite-email
verify_jwt: true (caller must be authenticated)
Path: supabase/functions/send-invite-email/index.ts
Behavior:
1. POST com body { invite_id: uuid, token: text, base_url: text }
2. Buscar invite em org_invites (RLS preserva permission)
3. Construir URL accept: <base_url>/invites/<token>
4. Enviar email via <email_provider> com:
- Subject: "Convite para <org.name>"
- Body: "Você foi convidado a entrar em <org.name>. Clique para aceitar: <url>. O link expira em <ttl_days> dias."
5. Retornar { sent: true }
Anti-pitfalls:
- ANON_KEY com JWT (não service_role)
- Token recebido via body, NÃO loggar token raw
- Email provider key via Deno.env (Vault secret)
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.
- 1mo ago First seen · 198 lines · 50 tokens per session scan A 74f541e5f23f
invite-flow-implementer is an agent published in the GitHub repository luanpdd/kit-mcp (5 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 2,206 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
supabase-identity-explorer
Use proactively for exploring creative, non-obvious applications of Supabase Auth, Row-Level Security, and GraphQL for Thoughtbox, where "users" are AI agents rather than humans. Specialist for generating surprising identity-dimension design proposals grounded in metaphors of theatrical masks, legal personhood, and…
backend-platform-engineer
Builds and reviews backend services — NestJS modules, APIs, Postgres access, Redis/BullMQ workers, async workflows. Use for implementation, code, tests, debugging and refactoring. Escalates architecture-level decisions to principal-engineer.
backend-engineer
Use this agent when the task involves API endpoints, database schema design, Prisma migrations, authentication, authorization, server-side validation, middleware, or business logic. For example: creating a new REST endpoint with request validation, adding a Prisma model and migration, implementing JWT auth with…
backend-engineer
Backend implementation. Use for API, authentication, DB migration work.
backend
Go backend specialist. OpenAPI-first, Echo handlers, Firestore, Cloud Run. Use for backend features, API design.
backend-dev
An agent for building and fixing server-side software, including APIs, business rules, databases, background jobs, authentication, and caching.