supabase-remote

A remote command-line tool for managing Supabase projects, including their PostgreSQL databases and access rules. Supabase is a hosted platform built around PostgreSQL, and row-level security controls which rows users can access.

In plain words
What is it for?
Use it to list or select projects, run SQL, verify changed rows, audit row-level security, and generate TypeScript types from Supabase databases.
Why use it?
It brings common remote project checks and database tasks into repeatable commands. It can also verify query results, inspect row-level security, and generate TypeScript database types.

Plugin 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.

Claude Code
/plugin marketplace add osouthgate/agent-plus-skills
agentmods
npx agentmods add plugins/osouthgate/agent-plus-skills/supabase-remote
Clone the repo
git clone --depth 1 https://github.com/osouthgate/agent-plus-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 72 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

supabase-remote 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 2d 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.

supabase-remote/.claude-plugin/plugin.json · 29 lines

What it actually says

{
  "name": "supabase-remote",
  "description": "Remote CLI for day-to-day Supabase project ops — project list/resolve, SQL exec with JSON-envelope stripping and post-run row verification, RLS audit, TypeScript gen-types. Wraps the Management API + `supabase` CLI.",
  "version": "0.5.0",
  "author": {
    "name": "Oliver Southgate",
    "url": "https://github.com/osouthgate"
  },
  "homepage": "https://github.com/osouthgate/agent-plus-skills",
  "repository": "https://github.com/osouthgate/agent-plus-skills",
  "license": "MIT",
  "keywords": [
    "supabase",
    "postgres",
    "rls",
    "cli",
    "remote",
    "sql",
    "management-api"
  ],
  "agent_plus_version": ">=0.7",
  "refresh_handler": {
    "command": "supabase-remote whoami --json",
    "timeout_seconds": 10,
    "identity_keys": ["linked_project_ref", "projects"],
    "failure_mode": "soft"
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 72 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 2d ago First seen · 29 lines scan A 0a34406d92f0

Subscribe to this mod's changes

supabase-remote is a plugin published in the GitHub repository osouthgate/agent-plus-skills (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.