supabase-as-a-service: Instructions file for Claude Code

CLAUDE.md

supabase-as-a-service CLAUDE.md is an instructions file for Claude Code from alnutile/supabase-as-a-service. It costs 31,322 tokens per session, scanned C, original, MIT.

Repository instructions for a React intranet built on Supabase, a hosted backend that provides authentication, databases, file storage, and live updates. The app also includes an AI chat assistant and shareable documents, code, and HTML artifacts.

In plain words
What is it for?
Running, building, linting, type-checking, testing, and regenerating database types for the React app and its Supabase server functions.
Why use it?
They explain where security-sensitive code runs, how browser access is protected, and which checks are required before committing changes. This reduces the risk of breaking the app or exposing server-only keys.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is alnutile/supabase-as-a-service's own configuration. It tells Claude Code how to work on supabase-as-a-service itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything supabase-as-a-service configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alnutile/supabase-as-a-service. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alnutile/supabase-as-a-service/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alnutile/supabase-as-a-service

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 supabase-as-a-service CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alnutile/supabase-as-a-service/claude-md/github.svg)](https://agentmods.dev/instructions/alnutile/supabase-as-a-service/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alnutile/supabase-as-a-service/claude-md"><img src="https://agentmods.dev/badge/instructions/alnutile/supabase-as-a-service/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for supabase-as-a-service CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alnutile/supabase-as-a-service/claude-md"><img src="https://agentmods.dev/badge/instructions/alnutile/supabase-as-a-service/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31,322 This file is loaded in full into every session.
When invoked 31,322 The same file — it is already loaded in full.
Security scan C 2 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 $0.31322 $0.31322
Opus 5 $0.15661 $0.15661
Sonnet 5 $0.06264 $0.06264
Haiku 4.5 $0.03132 $0.03132

Measured 5d ago against content hash 859e9fc5e6c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

supabase-as-a-service CLAUDE.md scanned grade C with 2 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 5d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

bespoke endpoint. Install `curl -fsSL .../install.sh | sh` or `npm i -g supanet-cli`; configure

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

non‑Claude systems (scripts, Zaps, cron) can push/sync artifacts with a `curl` instead of
CLAUDE.md · 1,375 lines

How it starts

The opening of the file, as written. The whole thing — 1,375 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI agents (and humans) working in this repository.

What this is

A React intranet layer on top of Supabase: auth, an AI chat assistant, shareable "artifacts" (docs/code/HTML), file storage, and live realtime updates. The OpenRouter key is server-side only (a Supabase Edge Function); the browser holds just the Supabase anon key and is protected by Postgres row-level security.

Two companion repos live outside this one and are worth offering when someone asks how to reach a workspace from elsewhere: the supanet CLI (terminal/script/cron/shell-capable agent) and supanet-skills (portable Agent Skills for Claude Code / pi / Codex). See Companion repos below.

Commands

npm install            # install deps
npm run dev            # Vite dev server on http://localhost:5173
npm run build          # tsc -b (typecheck) + vite build — run before pushing
npm run lint           # eslint
npm run typecheck      # tsc -b --noEmit
npm test               # vitest (frontend unit tests: src/**/*.test.ts(x))
npm run test:deno      # deno test supabase/functions/tests/ (edge-function units)
npm run gen:types      # regenerate src/lib/database.types.ts from the linked project
npm run start          # serve dist/ with SPA fallback (production / Railway)

Always run npm run build before committing UI/logic changes — it typechecks the whole app. Run npm test (and npm run test:deno if you touched supabase/functions/) too; add tests when you add or change logic (parsing, validation, calculations). Testable logic is kept out of components/handlers on purpose — the :::artifact protocol parser lives in src/lib/artifacts.ts (not ChatPage), webhook payload validation in supabase/functions/_shared/validate.ts, the p page's HTML/state injection in supabase/functions/p/meta.ts — follow that pattern: extract pure logic, test the module. CI (.github/workflows/test.yml) runs lint + build + both suites on PRs and pushes to main; claude-feature.yml runs the same checks against the bot-built branch (its PRs can't trigger PR workflows — GITHUB_TOKEN anti-recursion).

Read the full file on GitHub · 1,375 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. 5d ago Changed · +65 lines · +1,535 tokens per session scan A → C 859e9fc5e6c4
  2. 9d ago First seen · 1,310 lines · 29,787 tokens per session scan A 48d0759d3b0e

Subscribe to this mod's changes

supabase-as-a-service CLAUDE.md is an instructions file published in the GitHub repository alnutile/supabase-as-a-service (5 stars, last pushed yesterday), licensed MIT. It adds 31,322 tokens to every session, about $0.1566 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens