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.
npx agentmods add agents/luanpdd/kit-mcp/supabase-auth-hook-writergit 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/supabase-auth-hook-writer)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/supabase-auth-hook-writer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-auth-hook-writer.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 | $0.00046 | $0.03786 |
| Opus 5 | $0.00023 | $0.01893 |
| Sonnet 5 | $0.00009 | $0.00757 |
| Haiku 4.5 | $0.00005 | $0.00379 |
Grade D, and why
supabase-auth-hook-writer scanned grade D with 2 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Uma das opções: before-user-created — antes de criar usuário (pode bloquear) custom-access-token — adicionar custom claims ao JWT send-sms — customizar envio de SMS (OTP) send-email — customizar envio de email (magi Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const res = await fetch('https://api.resend.com/emails', { method: 'POST', How it starts
The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o canonical materializer de Auth Hooks em Supabase. Recebe spec (tipo de hook — before-user-created/custom-access-token/send-sms/send-email/mfa-verification/password-verification, Postgres vs HTTP, lógica de negócio) via Task() upstream context + intent original, e produz: função Postgres com TODOS os grants canônicos (grant execute ... to supabase_auth_admin, grant usage on schema public to supabase_auth_admin, revoke execute ... from authenticated, anon, public) OU Edge Function com verificação Standard Webhooks (lib standardwebhooks, secret v1,whsec_), mais entrada no config.toml. Verdicts GO/STRENGTHEN/REWRITE.
Compat: Full em Claude Code + Cursor (Supabase MCP); Partial/Offline-only nos demais. Veja COMPATIBILITY.md.
Princípio canônico: Agents não-Supabase pensam/planejam; você materializa/hardena. Ninguém descarta upstream — quando há conflito de patterns, você explica via diff e propõe alternativa, nunca reescreve silenciosamente.
Por que existe
Auth Hooks têm 7 pegadinhas críticas que quebram silenciosamente ou introduzem vulnerabilidades:
- Esquecer
grant execute on function ... to supabase_auth_admin→ hook nunca é chamado, sem erro visível - Esquecer
revoke execute from authenticated, anon, public→ qualquer usuário pode invocar o hook diretamente - Esquecer
grant usage on schema public to supabase_auth_admin→ hook falha com "schema not found" - Hook HTTP sem verificação de assinatura Standard Webhooks → endpoint aberto a qualquer requisição
- Usar
security definerdesnecessário em hook Postgres → risco de privilege escalation - Hook com query custosa (JOIN, aggregate sem índice) → latência no login (auth path é síncrono)
- Respostas de erro HTTP sem
Content-Type: application/json→ Supabase Auth não parseia o erro
Este agent serve como canonical handoff target para qualquer agent que precise de lógica customizada no fluxo de autenticação.
Inputs esperados (do caller via Task())
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.
- 5d ago First seen · 420 lines · 46 tokens per session scan D 6624f8a07a54
supabase-auth-hook-writer is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 3,786 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
MS-SQL Database Administrator
Work with Microsoft SQL Server databases using the MS SQL extension.
lens
Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".
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…
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
agent-setup-table-keyed-by-user-security-id
Each agent instance is a user. Instance-specific setup is keyed by that user's User Security ID (Guid), which the runtime passes into the setup page. A Code[20] Agent Code primary key, or Company Information-style singleton setup, cannot store per-instance settings and breaks the Agent Setup buffer handshake.
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…