butterbase-skills: Instructions file for Claude Code

CLAUDE.md

butterbase-skills CLAUDE.md is an instructions file for Claude Code from butterbase-ai/butterbase-skills. It costs 3,437 tokens per session, scanned A, original, MIT.

Project guidance for Butterbase, an AI-focused backend service that lets agents set up databases, user sign-in, file storage, and server-side functions through tools. It also explains required environment settings and documentation checks.

In plain words
What is it for?
Use it when building or changing Butterbase database schemas, authentication, access rules, storage, functions, AI features, frontends, billing, or integrations.
Why use it?
It keeps platform-related changes aligned with Butterbase’s documented interfaces and discourages putting platform-specific code in the wrong package.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is butterbase-ai/butterbase-skills's own configuration. It tells Claude Code how to work on butterbase-skills 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 butterbase-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to butterbase-ai/butterbase-skills. 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/butterbase-ai/butterbase-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/butterbase-ai/butterbase-skills

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 butterbase-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/butterbase-ai/butterbase-skills/claude-md/github.svg)](https://agentmods.dev/instructions/butterbase-ai/butterbase-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/butterbase-ai/butterbase-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/butterbase-ai/butterbase-skills/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 butterbase-skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/butterbase-ai/butterbase-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/butterbase-ai/butterbase-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,437 This file is loaded in full into every session.
When invoked 3,437 The same file — it is already loaded in full.
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 $0.03437 $0.03437
Opus 5 $0.01718 $0.01718
Sonnet 5 $0.00687 $0.00687
Haiku 4.5 $0.00344 $0.00344

Measured 13d ago against content hash b28caa4b5ebf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

butterbase-skills CLAUDE.md 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 13d 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.

CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Butterbase

You are working with Butterbase, an AI-Native Backend-as-a-Service. Butterbase lets AI agents provision databases, manage schemas, configure auth, deploy serverless functions, and manage storage — all through MCP tools.

Environment Variables

Variable Description Example
BUTTERBASE_API_KEY Platform API key (service role, bypasses RLS) bb_sk_a1b2c3...
CONTROL_API_URL API base URL (default: https://api.butterbase.ai) http://localhost:4000
VITE_API_URL Frontend env: API URL for Vite/React apps https://api.butterbase.ai/v1/app_abc123
VITE_APP_ID Frontend env: App ID for Vite/React apps app_abc123

Always Check Docs Before Platform Work

Before any stage that touches a Butterbase capability (schema, auth, RLS, storage, functions, AI, RAG, realtime, durable objects, frontend, billing, integrations, substrate), do both:

  1. Call butterbase_docs with the matching topic (see table in the Guided Journey section).
  2. WebFetch https://docs.butterbase.ai/<area> when you need human-facing context (URLs, prose, example apps, screenshots) — the MCP doc is the source of truth for API shapes, the website is the source of truth for narrative.

Re-consult whenever you hit an unfamiliar error, are about to invent an API shape, or the user's plan calls for a capability you haven't worked with this session.

Toolchain — SDK and CLI

Three surfaces work together. Pick the right one per task:

Surface What it's for When to use it
MCP tools (this plugin) Provisioning, schema, RLS, OAuth setup, function deploy, frontend deploy, integrations, billing config Orchestration tasks — anything that mutates platform state. The agent's primary surface.
@butterbase/sdk Runtime client: auth, db queries, storage, realtime, function invocation. Works in browser AND Node. All application code. Frontends. Server-side scripts. Functions that talk to other apps. Never hand-roll fetch against the REST API in a Butterbase app.
@butterbase/cli Local dev loop: project scaffolding, log tailing, function invocation, key generation, schema diff preview The human developer's terminal. Install globally once per machine.

Read the full file on GitHub · 209 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. 13d ago First seen · 209 lines · 3,437 tokens per session scan A b28caa4b5ebf

Subscribe to this mod's changes

butterbase-skills CLAUDE.md is an instructions file published in the GitHub repository butterbase-ai/butterbase-skills (533 stars, last pushed 2mo ago), licensed MIT. It adds 3,437 tokens to every session, about $0.0172 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 2026-08-30.

Related

Other instructions, from other repositories