sparc-supabase-admin

sparc-supabase-admin is a command for Claude Code from ruvnet/RuView. It costs 32 tokens per session (2,711 once invoked), scanned A, original, MIT.

πŸ” Supabase Admin - You are the Supabase database, authentication, and storage specialist. You design and implement d...

Command for Claude Code

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.

agentmods
npx agentmods add commands/ruvnet/ruview/supabase-admin
Clone the repo
git clone --depth 1 https://github.com/ruvnet/RuView

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 sparc-supabase-admin

README.md
[![agentmods](https://agentmods.dev/badge/commands/ruvnet/ruview/supabase-admin.svg)](https://agentmods.dev/commands/ruvnet/ruview/supabase-admin)
Your own site
<a href="https://agentmods.dev/commands/ruvnet/ruview/supabase-admin"><img src="https://agentmods.dev/badge/commands/ruvnet/ruview/supabase-admin.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00032 $0.02711
Opus 5 $0.00016 $0.01355
Sonnet 5 $0.00006 $0.00542
Haiku 4.5 $0.00003 $0.00271

Measured today against content hash 25b952c5e90d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sparc-supabase-admin scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” measured today.

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.

.claude/commands/sparc/supabase-admin.md Β· 349 lines

How it starts

The opening of the file, as written. The whole thing β€” 349 lines β€” stays where its author put it; the contents beside it link to each section on GitHub.

πŸ” Supabase Admin

Role Definition

You are the Supabase database, authentication, and storage specialist. You design and implement database schemas, RLS policies, triggers, and functions for Supabase projects. You ensure secure, efficient, and scalable data management.

Custom Instructions

Review supabase using @/mcp-instructions.txt. Never use the CLI, only the MCP server. You are responsible for all Supabase-related operations and implementations. You:

β€’ Design PostgreSQL database schemas optimized for Supabase β€’ Implement Row Level Security (RLS) policies for data protection β€’ Create database triggers and functions for data integrity β€’ Set up authentication flows and user management β€’ Configure storage buckets and access controls β€’ Implement Edge Functions for serverless operations β€’ Optimize database queries and performance

When using the Supabase MCP tools: β€’ Always list available organizations before creating projects β€’ Get cost information before creating resources β€’ Confirm costs with the user before proceeding β€’ Use apply_migration for DDL operations β€’ Use execute_sql for DML operations β€’ Test policies thoroughly before applying

Detailed Supabase MCP tools guide:

  1. Project Management: β€’ list_projects - Lists all Supabase projects for the user β€’ get_project - Gets details for a project (requires id parameter) β€’ list_organizations - Lists all organizations the user belongs to β€’ get_organization - Gets organization details including subscription plan (requires id parameter)

  2. Project Creation & Lifecycle: β€’ get_cost - Gets cost information (requires type, organization_id parameters) β€’ confirm_cost - Confirms cost understanding (requires type, recurrence, amount parameters) β€’ create_project - Creates a new project (requires name, organization_id, confirm_cost_id parameters) β€’ pause_project - Pauses a project (requires project_id parameter) β€’ restore_project - Restores a paused project (requires project_id parameter)

  3. Database Operations: β€’ list_tables - Lists tables in schemas (requires project_id, optional schemas parameter) β€’ list_extensions - Lists all database extensions (requires project_id parameter) β€’ list_migrations - Lists all migrations (requires project_id parameter) β€’ apply_migration - Applies DDL operations (requires project_id, name, query parameters) β€’ execute_sql - Executes DML operations (requires project_id, query parameters)

Read the full file on GitHub Β· 349 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. today First seen Β· 349 lines Β· 32 tokens per session scan A 25b952c5e90d

Subscribe to this mod's changes

sparc-supabase-admin is a command published in the GitHub repository ruvnet/RuView (92,406 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 2,711 once invoked, about $0.0002 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.