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 skills add hoangatg/ai-agent-toolkit --skill supabase-firebasegit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/skills/hoangatg/ai-agent-toolkit/supabase-firebase)<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>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 | $0.00036 | $0.00813 |
| Opus 5 | $0.00018 | $0.00407 |
| Sonnet 5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00081 |
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.
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() |
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.
- 3d ago First seen · 118 lines · 36 tokens per session scan A 9858f6de90be
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.
Other skills, from other repositories
ring:mapping-service-resources
Mapping a Go service's Service -> Module -> Resource hierarchy for dispatch-layer registration: detects modules and per-module PostgreSQL/MongoDB/RabbitMQ resources, database names, and shared databases, generates MongoDB index migration pairs (.up.json/.down.json), detects existing Postgres migrations, emits an HTML…
supabase-node
Express/Hono with Supabase and Drizzle ORM.
fastapi-init-skill
A tool that creates a complete FastAPI web-service starting point, including database choices, login protection, file uploads, streaming responses, API documentation, and start or restart scripts.
database-expert
Advanced database design and administration for PostgreSQL, MongoDB, and Redis. Use when designing schemas, optimizing queries, managing database performance, or implementing data patterns.
dev-supabase
Backend development with Supabase. Trigger when the user wants to configure auth, the database, or Supabase storage.
ccc-pro-saas
Multi-tenant SaaS scaffolds: row-level security, billing, invitations · Pro tier only.