How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
AbilityaiCLAUDE.mdAbilityai/trinity/CLAUDE.md
feedback technically before implementing ### 7. Architectural Invariants Before adding endpoints, services, DB tables, or frontend views, review the Architectural Invariants section in @docs/memory/architecture.md — the always-loaded core, which also carries
wuxiranCLAUDE.mdwuxiran/cc-pane/CLAUDE.md
架构与数据流 ``` React Component → Zustand Store → Service (invoke) → Tauri IPC → Command → Service → Repository → SQLite/FS ``` ``` ┌─────────────────────────────────────────────────────────────┐ │ React Frontend │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌───────────────┐ │ │ │ Sidebar │ │ Panes │ │ Panels │ │ UI Components │ │ │ └────┬─────┘ └────┬─────┘ └────┬─────┘ └───────────────┘ │ │ │ │ │ │ │ ┌────┴─────────────┴────────────┴────┐ │ │ │ Services (invoke) + Stores │ │ │ └────────────────┬───────────────────┘ │ ├───────────────────┼─────────────────────────────────────────┤ │ Tauri IPC │ │ ├───────────────────┼─────────────────────────────────────────┤ │ Rust Backend │ │ │ ┌────────────────┴───────────────────┐ │ │ │ Commands → Services → Repository
agnt-ggCLAUDE.mdagnt-gg/agnt/CLAUDE.md
agent framework for building, deploying, and orchestrating intelligent workflows. It combines a Vue.js frontend, Express.js backend, and Electron shell to provide a cross-platform desktop application for managing AI agents
nirholasCLAUDE.mdnirholas/XActions/xspace-agents/CLAUDE.md
OpenAPI spec, memory system. x-spaces/ → Low-level Puppeteer automation scripts (JavaScript, legacy). public/ → Frontend HTML/CSS/JS for dev server (npm run dev). NOT used in production. ⚠️ Railway production serves from
butterbase-aiCLAUDE.mdbutterbase-ai/butterbase-skills/CLAUDE.md
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
paulrobelloCLAUDE.mdpaulrobello/claude-office/CLAUDE.md
make install # Install all dependencies make dev-tmux # Run in tmux (recommended) - backend :8000, frontend :3000 make dev-tmux-kill # Kill tmux session make checkall # Lint, typecheck, test all components
tony1223CLAUDE.mdtony1223/better-agent-terminal/CLAUDE.md
rust` - For local packaging verification without macOS signing/notarization: `pnpm run tauri:build:debug` ## Logging - **Frontend (renderer)**: Use `window.batAppAPI.debug.log(...)` instead of `console.log()`. This sends logs to the Tauri host logger, which
VikashLoombaCLAUDE.mdVikashLoomba/copilot-mcp/CLAUDE.md
string, command: string, args: string[], env: Record<string, string>, inputs: InstallConfigInput[] }, error?: string } ``` 3. **Frontend Processing**: - `SearchMCPServers` renders results immediately without CloudMCP details - Each `RepoCard` fetches its own CloudMCP details
MagicCubeCLAUDE.mdMagicCube/agentara/web/CLAUDE.md
Claude Code (claude.ai/code) when working with code in this repository. This is the frontend of Agentara (web/). See the parent ../CLAUDE.md and ../docs/overview.md for overall project context. ## Commands ```bash
claude-did-thisCLAUDE.mdclaude-did-this/claude-hub/CLAUDE.md
Type**: bug, feature, enhancement, documentation, question, security - **Complexity**: trivial, simple, moderate, complex - **Component**: api, frontend, backend, database, auth, webhook, docker **Process Flow:** 1. New issue triggers `issues.opened` webhook 2. Dedicated
HainrixzCLAUDE.mdHainrixz/the-architect/CLAUDE.md
Frame it as **"Here's what I'd build"** — not "here are your options." - Frontend in scope? Use `ui-ux-pro-max` for palette, type pairing and component style; `emil
fdmtlCLAUDE.mdfdmtl/director/CLAUDE.md
powered by better-auth. In development, we have two components: apps/studio which is the frontend. And apps/gateway that's the backend. You can start the frontend by running
saltboCLAUDE.mdsaltbo/agent-kanban/CLAUDE.md
while its inputs remain unchanged. The implementer may update both source and tests; a frontend edit alone does not require new E2E tests or a fixed sequence of specialist agents
duolahyperchoCLAUDE.mdduolahypercho/fusion-fable/CLAUDE.md
# Claude Fable 5 — System Prompt --- Claude should never use {antml:voice_note} blocks, even
antflydbCLAUDE.mdantflydb/antfly/CLAUDE.md
paths for provisioned, serverless, and embedded Lite deployments. ## Commands ```bash make build # All binaries + frontend + codegen make generate # After OpenAPI/proto changes (SDKs, docs, protobufs) ``` ## Testing **Zig tests and E2E suites
antflydbCLAUDE.mdantflydb/antfly/ts/CLAUDE.md
Agent Notes ## What this directory is TypeScript workspace for every Antfly frontend surface: the public SDK, unstyled search primitives, the shared design system, the graph widgets, the npm CLI wrappers
mudriiCLAUDE.mdmudrii/openclaw-dashboard/CLAUDE.md
Development Standards Zero-dependency Go HTTP server with embedded SPA frontend for OpenClaw bot metrics. ## Project Constraints - **Zero third-party dependencies** — `go.mod` has no `require` block, no `go.sum
HainrixzCLAUDE.mdHainrixz/open-carrusel/CLAUDE.md
Carrusel AI-powered Instagram carousel builder. Next.js 16 + React 19 + TypeScript + Tailwind v4. ## Architecture - **Frontend**: React app at localhost:3000 with chat panel (left), carousel preview (center), slide filmstrip (bottom
peterfeiCLAUDE.mdpeterfei/ai-agent-team/.claude/CLAUDE.md
位置：`.claude/agents/tech-leader.md` 2. **产品经理智能体** - `/agent product_manager` - 负责产品规划、需求分析和路线图制定 - 位置：`.claude/agents/product_manager.md` 3. **前端开发智能体** - `/agent frontend_dev` - 负责前端开发、UI实现和客户端逻辑 - 位置：`.claude/agents/frontend_dev.md` 4. **后端开发智能体** - `/agent backend_dev` - 负责后端开发、API设计和服务器端逻辑 - 位置：`.claude/agents/backend_dev.md
NgxbaCLAUDE.mdNgxba/claude-code-cli-ui/CLAUDE.md
preview # Preview production build # Type Checking bun run typecheck # Run TypeScript type checking ``` ## Architecture ### Frontend (Nuxt 3 + Vue 3) **Pages** (`app/pages/`): - `/agents` - List and manage agents - `/agents/[slug]` - Edit individual
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.
