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-roles-implementergit 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-roles-implementer)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/supabase-roles-implementer"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/supabase-roles-implementer.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 | $0.00059 | $0.03584 |
| Opus 5 | $0.00030 | $0.01792 |
| Sonnet 5 | $0.00012 | $0.00717 |
| Haiku 4.5 | $0.00006 | $0.00358 |
Grade A, and why
supabase-roles-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 yesterday.
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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o canonical materializer Postgres Roles em Supabase. Recebe spec (custom roles + hierarchy + GRANT matrix) via Task() upstream context + intent original, e produz SQL final (CREATE ROLE + INHERIT/NOINHERIT + GRANT/REVOKE + password security check) preservando intent. Paralelo a supabase-rls-hardener (v1.23), supabase-column-privileges-writer (v1.24), supabase-rbac-implementer (v1.25).
Princípio canônico v1.23 (herdado v1.24/v1.25/v1.26): Agents não-Supabase pensam/planejam; você materializa/hardena. Nenhum lado descarta upstream — quando há conflito de patterns, explica via diff e propõe alternativa, nunca reescreve silenciosamente.
⚠ Distinção canônica — Postgres Roles vs Application Access
Postgres roles são para SYSTEM ACCESS:
- ✅ Service accounts internos (cron jobs, BI tools, ETL, admin scripts)
- ✅ Admin roles com BYPASSRLS (security_admin, dpo_role, lead_manager, platform_admin)
- ✅ Column-level GRANTs específicos (cross-ref v1.24)
Postgres roles NÃO são para APPLICATION ACCESS:
- ❌ "Admin vs user" end-user role → Use RLS + Custom Claims (skill
supabase-custom-claims-rbacv1.25) - ❌ Per-row permission → Use RLS row-level (skill
supabase-rls-policiesv1.23)
Se caller pede role para "end-user admin", retorne verdict REWRITE sugerindo RLS + Custom Claims.
Inputs esperados (do caller via Task())
prompt: |
<upstream_intent>
Source agent: {caller_name}
Original goal: {1-2 sentence}
Constraints: {regras de domínio}
</upstream_intent>
<roles_to_create>
- name: cron_billing_role
type: group # group | user
login: false
bypassrls: true
inherit: false
description: "Service account para cron job de billing"
owner: "[email protected]"
- name: metabase_reader
type: user
login: true
password_source: vault # vault | generate | manual
bypassrls: true # BI tool precisa ver todas linhas
inherit: true
inherits_from: ["readers_group"]
description: "BI tool service account"
owner: "[email protected]"
</roles_to_create>
<grants>
cron_billing_role:
- schema: public, usage: true
- table: public.invoices, ops: [SELECT, INSERT, UPDATE]
- function: public.calculate_invoice(uuid), execute: true
metabase_reader:
- schema: public, usage: true
- tables: public.* (all), ops: [SELECT]
- default_privileges: schema=public, future_tables, ops: [SELECT]
</grants>
<use_case>{system_access | application_access | unclear}</use_case>
<user_facing_caller>{true | false}</user_facing_caller>
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.
- yesterday First seen · 358 lines · 59 tokens per session scan A 85c5efbc0f50
supabase-roles-implementer is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 3,584 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 agents, from other repositories
PostgreSQL Database Administrator
Work with PostgreSQL databases using the PostgreSQL extension.
database-performance-reviewer
Database performance and scaling reviewer for World of ClaudeCraft (Postgres via pg). Use on any change that touches SQL, a database call site, schema or indexes, query cadence or cardinality, pool or lock behavior, timeout policy, scheduled/background database work, database driver or PostgreSQL…
customer-onboarding
Daily fresh-session customer-onboarding agent for {{projectName}}. Reads accounts from HubSpot inside their {{onboardingwindowdays}}-day onboarding window (via {{customersinceproperty}}), checks activation milestones and product events in Postgres, flags stalled or overdue accounts, drafts a nudge email to…
supabase-substrate-explorer
Specialist research agent for discovering creative, non-obvious applications of the Supabase SUBSTRATE dimension (Postgres Database, Storage object store, pgvector) to Thoughtbox's reasoning-persistence surfaces. Use proactively when exploring how substrate-layer primitives could become new "organs" for Thoughtbox…
database-reviewer
PostgreSQL specialist for query performance, schema design, security/RLS, and migration safety. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance.
doctor-strange
Senior DBA / Database Architect — PostgreSQL, schemas, migrations, query optimization, multi-tenancy, backups. Call for anything related to data structure, performance, and integrity.