Editor
BabylonJS/Editor/CLAUDE.md
project's assets, geometries, scenes and scripts, plus S3 upload helpers. - `mcp/` — `babylonjs-editor-mcp-server`: MCP server exposing editor scene-composition capabilities to AI agents (see `mcp/specifications.md
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.
BabylonJS/Editor/CLAUDE.md
project's assets, geometries, scenes and scripts, plus S3 upload helpers. - `mcp/` — `babylonjs-editor-mcp-server`: MCP server exposing editor scene-composition capabilities to AI agents (see `mcp/specifications.md
asklokesh/claudeskill-loki-mode/CLAUDE.md
when needed - `docs/dev/project-structure.md` - directory map, codebase knowledge graph, key functions, critical data flow, the MCP server (`mcp/server.py`, 48 tools). - `docs/dev/architecture-reference.md` - the 8 quality gates, legacy healing, memory system, metrics
Onelevenvy/flock/CLAUDE.md
Anthropic, AWS Bedrock, Google Vertex - **Database**: SQLite via sqlx for sessions, conversations, providers, tools, MCP servers, workflows - **Async Runtime**: Tokio - **Sandbox**: Daytona cloud container runtime for isolated code execution - **Browser
MaxBittker/rs-sdk/CLAUDE.md
install` (from project root) 2. Open project in your AI coding tool — the MCP server will be available automatically 3. Control your bot with suggestions. ### Tools | Tool | Description | | ------------------------------ | ---------------------------------------------- | | `execute_code
CoolProp/CoolProp/CLAUDE.md
Linear Issues live in **Linear**, team **CoolProp** (issue key `COO`), reached through the Linear MCP server (`mcp__linear-server__*` tools). - Find work: `list_issues` with team `CoolProp`; read one with
MiguelsPizza/WebMCP/CLAUDE.md
/web](https://github.com/WebMCP-org/web)) Full-stack demo showcasing MCP-B capabilities: - **Frontend**: React with MCP server exposing todo management tools - **Backend**: Cloudflare Workers with Hono.js and PostgreSQL - **Real-time sync
dohsimpson/TaskTrove/CLAUDE.md
running, just skip this step and let the user know ## Tools **TypeScript MCP (Language Server Protocol):** Claude has access to LSP tools for enhanced code analysis and navigation: - `get_hover
Lazarus-AI/clearwing/CLAUDE.md
Spin up isolated Kali container, run commands, install tools - **mcp_tools** — Connect to external MCP servers - **dynamic_tool_creator** — Create new tools at runtime - **skill_tools** — Load Claude Code skills
ArcadeAI/arcade-mcp/CLAUDE.md
auth providers) ├── arcade-serve (Arcade Worker protocol: /worker/* REST endpoints, JWT auth, OpenTelemetry) │ └── arcade-mcp-server (MCPApp, MCPServer, Context, transports, resource server auth) │ └── arcade-mcp CLI (typer-based: new, login
boyter/cs/CLAUDE.md
matching, with relevance ranking (BM25/TF-IDF). Four modes: console output, interactive TUI, HTTP server, and MCP server. ## Build & Test Commands ```bash go build -o cs # Build binary go test
trohitg/MachinaOS/CLAUDE.md
managed local Android phone. | | **[MCP Connectors](./docs-internal/mcp_connectors.md)** | Custom connectors: the owner adds an outside MCP server from Connectors → Add, or the MCP server card in the Custom category (`mcp`, kind
borghei/Claude-Skills/CLAUDE.md
framework) + memory-tool/context-editing/reasoning-effort/caching upgrades to context-engine, llm-cost-optimizer, agent-workflow-designer, mcp-server-builder. Cross-platform surface unified — one `build_manifest.py` run regenerates `cli/skills.json`, `registry.json`, `.gemini/skills-index.json
Steady6 mentions in 2 weeks
No other project uses it yet
borghei/Claude-Skills/project-management/CLAUDE.md
1on1s/** - 1:1 templates by partner type (EM, designer, IC, manager) **Key Features:** - **Atlassian MCP Server** integration for direct Jira/Confluence operations - **Linear + Notion** integration patterns (GraphQL + REST) - **15+ Python
Steady6 mentions in 2 weeks
No other project uses it yet
docker/compose-for-agents/adk-sock-shop/CLAUDE.md
compose.yaml file, you should figure out which model you want to use, and which mcp servers are needed. - Create a service entry like the following: ```yaml mcp-gateway: image: docker/mcp-gateway
bytechefhq/bytechef/CLAUDE.md
both `com.fasterxml.jackson` and `tools.jackson` packages currently appear in deps), SpringDoc OpenAPI 3.0.3 ### Main Server Module Structure #### Core Modules (`server/libs/`) - **`atlas/`** - Workflow engine core - `atlas-coordinator/` - Orchestrates workflow execution - `atlas-execution
GetStream/stream-chat-flutter/CLAUDE.md
www.figma.com/design/BJppI3JYlPy3XeEu5MZY1E/SDK-Design-System) for the core components in `stream_core_flutter`. Use the Figma MCP server to look up designs when implementing or updating UI components. ## Sibling SDK Alignment Stream ships
liangdabiao/amazon-sorftime-research-MCP-skill/CLAUDE.md
Claude skills ## Sorftime MCP Integration ### API Configuration - **Config file**: `.mcp.json` - stores API key and endpoint - **Endpoint**: `https://mcp.sorftime.com?key={API_KEY}` - **Protocol**: `streamableHttp` using Server-Sent Events
losnoco/Cog/CLAUDE.md
Remote Control / MCP**: - `RemoteControl/` bootstraps and adapts the app to `CogRemoteControlTarget`. - `CogRemoteControl/` is the MCP server and tool handlers (`RemoteControlToolHandlers.swift`). It listens on a Unix socket (`ipc.sock
negokaz/excel-mcp-server/CLAUDE.md
internal/excel/pagination.go` ## File Structure ``` cmd/excel-mcp-server/ # Main application entry point internal/ excel/ # Excel abstraction layer server/ # MCP server implementation tools/ # MCP tool implementations launcher/ # TypeScript launcher memory-bank/ # Development context and progress
asdfghj1237890/HoloCubic_AIO/CLAUDE.md
frontend dev server (any of these): npx --yes http-server Docs/design/studio-flasher -p 8765 -c-1 --cors # quickest # OR via preview MCP: preview_start("studio-flasher") # OR: python -m http.server
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.