supabase-firebase

supabase-firebase is a skill for Claude Code, Codex from hoangatg/ai-agent-toolkit. It costs 36 tokens per session (813 once invoked), scanned A, original, MIT.

Backend-as-a-service guidance for building applications with Supabase or Firebase, which provide hosted user accounts, databases, file storage, and live data updates.

In plain words
What is it for?
Use it when building an app that needs login, data storage, file uploads, real-time updates, or server functions with Supabase or Firebase.
Why use it?
It helps you choose between the two platforms and avoid designing common backend pieces from scratch. It also explains access rules and server-side logic for each platform.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building an app that needs login, data storage, file…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangatg/ai-agent-toolkit/supabase-firebase
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.

Any agent
npx skills add hoangatg/ai-agent-toolkit --skill supabase-firebase
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

Made for: Claude Code, Codex.

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 supabase-firebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/supabase-firebase.svg)](https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/supabase-firebase)
Your own site
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/supabase-firebase"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/supabase-firebase.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 813 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 5.1 $0.00036 $0.00813
Opus 5 $0.00018 $0.00407
Sonnet 5 $0.00007 $0.00163
Haiku 4.5 $0.00004 $0.00081

Measured 3d ago against content hash 9858f6de90be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

supabase-firebase 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 3d 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.

.agent/skills/supabase-firebase/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Supabase & Firebase

Skip the backend boilerplate. Ship faster with managed services.


1. Platform Selection

Factor Supabase Firebase
Database PostgreSQL (SQL) Firestore (NoSQL)
Auth Built-in, OAuth, magic links Built-in, OAuth, phone
Real-time Postgres changes, broadcast Firestore listeners
Storage S3-compatible GCS-based
Functions Edge Functions (Deno) Cloud Functions (Node.js)
Self-host ✅ Docker ❌ Google only
Pricing Generous free tier Pay-as-you-go (can spike)
Best for SQL lovers, open-source Mobile apps, Google ecosystem

2. Supabase Patterns

Database (PostgreSQL)

Feature Use Case
Row Level Security Per-user data access
Realtime Subscribe to DB changes
Edge Functions Server logic (Deno runtime)
PostgREST Auto-generated REST API
Database Functions Business logic in SQL

RLS Design

Principle Application
Enable on all tables Default deny
Policy per operation SELECT, INSERT, UPDATE, DELETE
Use auth.uid() Match current user
Test policies Verify with different users

3. Firebase Patterns

Firestore Data Modeling

Pattern Use Case
Subcollections One-to-many (user → orders)
Denormalization Read-heavy, embed data
Collection groups Query across subcollections

Security Rules

Principle Application
Default deny No access without explicit rule
Validate writes Check data types and ranges
Limit reads Don't expose all data
Test rules Firebase Emulator Suite

4. Auth Integration

Supabase Auth

Method Implementation
Email/Password supabase.auth.signUp()
OAuth supabase.auth.signInWithOAuth()
Magic Link supabase.auth.signInWithOtp()
Row Level Security Auto-injected auth.uid()

Read the full file on GitHub · 118 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. 3d ago First seen · 118 lines · 36 tokens per session scan A 9858f6de90be

Subscribe to this mod's changes

supabase-firebase is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 813 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.