How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
LeantimeReads credentialsCLAUDE.mdLeantime/leantime/CLAUDE.md
interface. The application is built with PHP (Laravel), MySQL, and a JS frontend. Current version: 3.6.2. ## Current State & Active Migrations These are ongoing architectural efforts. None need to be fixed
No other project uses it yet
0xJackyCLAUDE.md0xJacky/nginx-ui/CLAUDE.md
project is a web-based NGINX management interface built with Go backend and Vue.js frontend. ## Package Manager - **Use Bun exclusively** for all frontend package management operations - Commands: `bun install
Steady6 mentions in 2 weeks
No other project uses it yet
grafanaCLAUDE.mdgrafana/pyroscope/ui/CLAUDE.md
Pyroscope UI React + Vite + TypeScript frontend for Pyroscope. This frontend is a rewrite of the old UI that lived in `public/app` (removed in the ui v2 migration; still available
blinkospaceReads credentialsCLAUDE.mdblinkospace/blinko/CLAUDE.md
multi-platform application (web, desktop via Tauri, mobile) built with TypeScript/React frontend and Node.js/Express backend. ## Tech Stack - **Frontend**: React 18, TypeScript, Vite, TailwindCSS, Tauri (for desktop apps) - **Backend**: Node.js
frappeCLAUDE.mdfrappe/frappe/ui/CLAUDE.md
real consuming app — keep the two stories in sync. Note CRM's frontend uses **2-space** indentation (its own prettier/eslint config), not this repo's tabs; run `npx prettier --write
bluewave-labsReads credentialsCLAUDE.mdbluewave-labs/Checkmate/CLAUDE.md
VITE_APP_LOG_LEVEL="debug" ``` ## Architecture ### Monorepo Structure - `/client` - React 18 + TypeScript + Vite + MUI frontend - `/server` - Node.js 24+ + Express + TypeScript backend - `/docker` - Multi-environment Docker configs (dev, staging, prod
Steady3 mentions in 2 weeks
No other project uses it yet
HeroToolsReads credentialsCLAUDE.mdHeroTools/open-whispr/CLAUDE.md
both local (privacy-focused) and cloud (OpenAI API) processing modes. ## Architecture Overview ### Core Technologies - **Frontend**: React 19, TypeScript, Tailwind CSS v4, Vite - **Desktop Framework**: Electron 41 with context isolation - **Database
StarTrail-orgCLAUDE.mdStarTrail-org/PixelRAG/CLAUDE.md
embed/`, `index/` — tiles → vectors → FAISS index - `serve/` — FAISS search API (`pixelrag serve`) - `web/` — Next.js frontend (on Vercel) + `agent-server.mjs` (the chat agent backend) - `train/` — **separate uv project** (LoRA finetune); install from
No other project uses it yet
FreikaReads credentialsCLAUDE.mdFreika/dawarich/CLAUDE.md
Authorization**: Pundit - **API Documentation**: rSwag (Swagger) - **Monitoring**: Prometheus, Sentry - **File Processing**: AWS S3 integration ### Frontend - **CSS Framework**: Tailwind CSS with DaisyUI components - **JavaScript**: Stimulus, Turbo Rails, Hotwired - **Maps**: MapLibre
Steady7 mentions in 2 weeks
No other project uses it yet
Saptha-meReads credentialsCLAUDE.mdSaptha-me/Bindu/CLAUDE.md
localhost (see `docs/MTLS_DEPLOYMENT_GUIDE.md`) - [ ] No automatic reconnection if SDK crashes - [ ] No connection pooling in GrpcAgentClient - [ ] Frontend needs OAuth2 integration with Hydra - [ ] Payment webhook verification needs improvement - [ ] Agent trust validation needs integration
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
