big-AGI: Instructions file for Claude Code

CLAUDE.md

big-AGI CLAUDE.md is an instructions file for Claude Code from enricoros/big-AGI. It costs 2,703 tokens per session, scanned A, original, MIT.

Repository instructions for big-AGI, a web application that lets users work with multiple AI models and combine their answers.

In plain words
What is it for?
Developing its Next.js pages and APIs, working with the Joy user interface, managing client-side chat data, and handling parallel model conversations.
Why use it?
They explain the unusual technology choices, data storage, model integrations, and development restrictions so changes match the existing application.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is enricoros/big-AGI's own configuration. It tells Claude Code how to work on big-AGI 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 big-AGI configures →

About the project

Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.

enricoros/big-AGI · 7,113 stars · on GitHub · big-agi.com

Reuse

Borrowing it

Nothing to install: this file belongs to enricoros/big-AGI. 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/enricoros/big-AGI/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/enricoros/big-AGI

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 big-AGI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/enricoros/big-agi/claude-md.svg)](https://agentmods.dev/instructions/enricoros/big-agi/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/enricoros/big-agi/claude-md"><img src="https://agentmods.dev/badge/instructions/enricoros/big-agi/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,703 This file is loaded in full into every session.
When invoked 2,703 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 $0.02703 $0.02703
Opus 5 $0.01352 $0.01352
Sonnet 5 $0.00541 $0.00541
Haiku 4.5 $0.00270 $0.00270

Measured 8d ago against content hash 82075d9ce0eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

big-AGI 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 8d 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance to Claude Code when working with code in this repository.

Architecture Overview

Stack: Next.js 15 (Pages Router for pages, App Router for API routes only), React 18, Emotion (CSS-in-JS), Zustand, tRPC + TanStack React Query, Edge runtime for AI and Node.js for data ops. UI is Material-UI Joy, not Material: import from @mui/joy; next.config.ts webpack-aliases @mui/material -> @mui/joy so stray/transitive Material imports still resolve to Joy (webpack only - turbopack skips that hook).

Distinctive, vs other chat UIs: Beam runs N models in parallel and fuses the answers (scatter/gather); every vendor sits behind one AIX protocol layer, reusing a few wire dialects instead of one integration each; chat is stored client-side in IndexedDB by default; BYO-keys (self-hosters may additionally set server-side vendor keys in env vars); AI calls can go browser-direct to the vendor (CSF); messages are typed fragments, not strings; personas and multi-pane conversations are first-class.

Development Commands

Dev servers may be already running on ports 3000, 3001, 3002, or 3003 (not always this app - other projects may occupy these ports). Never start or stop dev servers, let the user do it.

# Validate - safe while a dev server runs, and far quicker than `next build` for the same checks
npm run tscheck && npm run lint      # types (all projects), then a typed ESLint pass
eslint src/path/to/file.ts           # lint one file

# Full build - slow, only when suspecting runtime/bundle issues
npm run build  # compile+lint+types, but stops at the first type-error file; tsc shows all at once

For AI protocol development (model listing, live API requests/responses, parameter probing), real vendor API keys are in .env.api-keys if present (Anthropic, OpenAI, Gemini, etc., one VENDOR_API_KEY per line). Use them for empirical verification; never commit or echo the values.

Git/GitHub remotes

The gh command is available to interact with GitHub from the terminal, but NEVER PUSH TO ANY BRANCH. The user manages all 'write' git operations.

  • opensource -> enricoros/big-AGI (public, default branch: main, MIT) - community issues/PRs/releases
  • private -> big-agi/big-agi-private (private, default branch: dev) - main dev repo with dev->staging->prod pipeline
  • Always use git mv instead of mv when renaming or moving files - preserves git history tracking
  • NEVER run git stash - it causes work loss
  • Commit subjects: Area: terse imperative (e.g. LLMs: OpenAI: ..., Build: ...), single line, no body unless needed, and no Co-Authored-By trailer

Read the full file on GitHub · 132 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. 8d ago First seen · 132 lines · 2,703 tokens per session scan A 82075d9ce0eb

Subscribe to this mod's changes

big-AGI CLAUDE.md is an instructions file published in the GitHub repository enricoros/big-AGI (7,113 stars, last pushed yesterday), licensed MIT. It adds 2,703 tokens to every session, about $0.0135 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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens