OpenRoom: Instructions file for Claude Code

CLAUDE.md

OpenRoom CLAUDE.md is an instructions file for Claude Code from MiniMax-AI/OpenRoom. It costs 1,801 tokens per session, scanned A, original, MIT.

A development guide for OpenRoom, a React and TypeScript system for building small web apps that run inside an iframe.

In plain words
What is it for?
Use it when creating, changing, resuming, or verifying OpenRoom apps and their components, pages, data, assets, or storage.
Why use it?
It gives the required workflow stages, project layout, technologies, and commands, so changes fit the existing app structure.

Instructions file for Claude Code

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

This is MiniMax-AI/OpenRoom's own configuration. It tells Claude Code how to work on OpenRoom 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 OpenRoom configures →

About the project

OpenRoom is a browser-based desktop environment where an AI agent controls built-in applications through natural-language requests and structured actions. People use it to interact with tools such as music, email, diary, games, and other apps through a desktop-like interface running locally in the browser. Its catalogue add-ons provide commands and instructions for working with this environment.

MiniMax-AI/OpenRoom · 1,272 stars · on GitHub · openroom.ai

Reuse

Borrowing it

Nothing to install: this file belongs to MiniMax-AI/OpenRoom. 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/MiniMax-AI/OpenRoom/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MiniMax-AI/OpenRoom

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 OpenRoom CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/minimax-ai/openroom/claude-md"><img src="https://agentmods.dev/badge/instructions/minimax-ai/openroom/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,801 This file is loaded in full into every session.
When invoked 1,801 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 $0.01801 $0.01801
Opus 5.5 $0.00720 $0.00720
Sonnet 5.5 $0.00360 $0.00360
Haiku 4.5 $0.00180 $0.00180

Measured 2mo ago against content hash 0bb70fd9514f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OpenRoom 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 2mo 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeApp Development Guide

An iframe-based micro-frontend VibeApp system (React + Cloud NAS).

Quick Start

Create a new app: /vibe {AppName} {Description} Modify an existing app: /vibe {AppName} {ChangeDescription} Resume an existing workflow: /vibe {AppName} Re-run from a specific stage: /vibe {AppName} --from=04-codegen

Creation mode runs 6 stages: Requirement Analysis -> Architecture Design -> Task Planning -> Code Generation -> Asset Generation -> Project Integration. Change mode runs 4 stages: Change Impact Analysis -> Change Task Planning -> Change Code Implementation -> Change Verification. You can also enter a requirement description directly, and the system will automatically detect and trigger the corresponding mode.

Tech Stack

  • Framework: React 18 + TypeScript + Vite
  • Styling: Tailwind CSS (H5 Pages), CSS Modules (Components)
  • Icons: Lucide React (No Emoji)
  • Storage: Cloud NAS via @/lib (Repository Pattern)
  • Communication: postMessage via @/lib

File Structure

src/pages/{AppName}/
├── components/    # UI Components
├── pages/         # Sub-pages (H5 Templates)
├── data/          # Seed Data (JSON only)
├── assets/        # Generated Image Assets
├── mock/          # Dev Mock Data (TypeScript)
├── store/         # Context/Reducer
├── actions/       # Action Definitions
├── styles/        # CSS Variables
├── i18n/          # en.ts + zh.ts
├── meta/
│   ├── meta_cn/   # Chinese: guide.md + meta.yaml
│   └── meta_en/   # English: guide.md + meta.yaml
├── index.tsx      # Entry (lifecycle reports here only)
├── index.module.scss
└── types.ts

Workflow Structure

.claude/
├── commands/vibe.md           # Single entry orchestrator
├── workflow/
│   ├── stages/                # Stage definitions (loaded on-demand)
│   │   ├── 01-analysis.md          # Create: Requirement Analysis
│   │   ├── 02-architecture.md      # Create: Architecture Design
│   │   ├── 03-planning.md          # Create: Task Planning
│   │   ├── 04-codegen.md           # Create: Code Generation
│   │   ├── 05-assets.md            # Create: Asset Generation
│   │   ├── 06-integration.md       # Create: Project Integration
│   │   ├── 01-change-analysis.md       # Change: Impact Analysis
│   │   ├── 02-change-planning.md       # Change: Task Planning
│   │   ├── 03-change-codegen.md        # Change: Code Implementation
│   │   └── 04-change-verification.md   # Change: Verification
│   └── rules/                 # Stage-specific rules (loaded on-demand)
│       ├── app-definition.md
│       ├── responsive-layout.md
│       ├── guide-md.md
│       └── meta-yaml.md
├── rules/                     # Global rules (always loaded)
│   ├── data-interaction.md
│   ├── design-tokens.md
│   ├── concurrent-execution.md
│   └── post-task-check.md
└── thinking/{AppName}/        # Per-app workflow state & artifacts
    ├── workflow.json
    ├── 01-requirement-analysis.md
    ├── 02-architecture-design.md
    ├── 03-task-planning.md
    ├── 04-code-generation.md
    └── outputs/
        ├── requirement-breakdown.json
        ├── solution-design.json
        └── workflow-todolist.json

Read the full file on GitHub · 171 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. 2mo ago First seen · 171 lines · 1,801 tokens per session scan A 0bb70fd9514f

Subscribe to this mod's changes

OpenRoom CLAUDE.md is an instructions file published in the GitHub repository MiniMax-AI/OpenRoom (1,272 stars, last pushed 5mo ago), licensed MIT. It adds 1,801 tokens to every session, about $0.0072 per session on Opus 5.5. 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

OpenRoom CLAUDE.md compared with instructions from other repositories

OpenRoom CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
OpenRoom CLAUDE.mdMiniMax-AI/OpenRoomInstructions file1.3k5mo agoMITA1,801Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode