Rules

This file tells Claude Code (and other AI agents) how to work with this repository.

This file provides Claude Code with context about this project.

When I refer to issues like mipnix-rn3b checkout the task in @.beans/mipnix-rn3b-*.md In this project we will use these tasks as epics for making openspec proposals. WHEN you create a proposal at a link to this task in the proposal.md.

Rules in this file apply to every Claude Code session in this repo. They override generic defaults and persist across conversations.

Claude Code project instructions and development guidelines.

You are Claw, a personal AI assistant for your owner. You run as a Telegram bot powered by Claude Code. Concise, high-signal, engineer-to-engineer. Have opinions. Be resourceful. Earn trust through competence.

You are helping a chapter lead host a Humans in AI Week Discussion Night.

The reference atlas is [`docs/README.md`](docs/README.md); read the doc that covers what you are touching before touching it. **Before any styling work, read [`docs/design.md`](docs/design.md)** — `src/lib/components` is the most

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

You are working in a Higgsfield video production workspace. Your job is to run the content pipeline end to end: write prompts, fire renders, check keyframes with the user, and assemble final cuts. Read this file fully before generating anything.

You are working in a Childhood Cancer Data Lab repository. This project is an R package for interacting with the [Single-cell Pediatric Cancer Atlas (ScPCA) Portal](https://scpca.alexslemonade.org) API.

<!-- THE CLAUDE.MD BLUEPRINT TEMPLATE This is the master instruction file for Claude Code. When Claude opens your project, this is the first thing it reads. Think of it as the "operating system" for your AI assistant.

This is a **skills library for Abaqus secondary development** that follows the open [Agent Skills standard](https://agentskills.io) — structured knowledge organized as skills that AI agents (Claude Code, Codex, opencode, Gemini CLI, Cursor, etc.) can use to generate

> **You are Claude (Anthropic), running inside Claude Code CLI.** > **Model**: Claude Opus 4.6 / Sonnet 4.6 > **Aura Version**: v0.12.6 > **MCP Server**: aura-vcs (29+ tools available)

**AUREA** Claude Code stack (Next.js 16 + Go).

Modern responsive image management for projects using the Roots Acorn framework.

Build, test and box-routing guidance lives in **`AGENTS.md`** — read it. This file is one doctrine that overrides a default you almost certainly arrived with.

This repo IS Attacca: a Claude Code plugin marketplace (three plugins) plus a 4-file project template. You are editing the product, not using it. The plugin hooks/skills here are content, not instructions to follow.

This repository uses the Engineering OS harness. <!-- engineering-os:start --> @.claude/engineering-os/constitution.md @.claude/engineering-os/workflow.md <!-- engineering-os:end -->

This module handles live credentials: the customer's Pinecone API key, a cpgw API key, a Datadog API key, and cloud credentials. The e2e harness streams command output to a log file, prints it to stdout, and uploads it

This repo is the design file. Everything about this product — brief, research, structure, screens, voice, visual language, system, handoff — lives here as files, not in chat history. Read this file first, then the artifacts it points to. Never re-ask what is already written.

Before doing ANYTHING (including reading files or planning), you MUST run: npm run omnirule:init **Why?** This command activates the `DesignVault`, loads project skills, and prepares the mandatory orchestration layer. If you skip this, the system will block your further actions via Hookify.