CLAUDE.md examples from real projects

Team-CommonlyReads credentialsCLAUDE.md

commonly

Team-Commonly/commonly/CLAUDE.md

commonly_dm_agent`. - **A `commonly_*` tool name does NOT identify a capability.** The MCP server and the openclaw extension tool sets diverge, and one name can mean two things: `commonly

miscusi-peekCLAUDE.md

cheatengine-mcp-bridge

miscusi-peek/cheatengine-mcp-bridge/CLAUDE.md

Table Lua Script`; in that case execute `dofile([[C:\path\to\cheatengine-mcp-bridge\MCP_Server\ce_mcp_bridge.lua]])` instead of pasting the full bridge. Success log: `[MCP v12.0.0] MCP Server Listening

Prismer-AIReads credentialsCLAUDE.md

PrismerCloud

Prismer-AI/PrismerCloud/CLAUDE.md

multi-language client SDKs and plugins (AIP identity + Prismer Cloud platform families). > **Note:** The server backend is closed-source and is **not** included in this public repository. This repo

nanobot-aiCLAUDE.md

nanobot

nanobot-ai/nanobot/CLAUDE.md

ChatGPT, Nanobot is designed to be an open-source, deployable solution that combines MCP servers with LLMs to create agent experiences through external interfaces such as Obot. The project

ruzinCLAUDE.md

stenoai

ruzin/stenoai/CLAUDE.md

user installs and grants access, serves it over MCP. `app/imcp-client.js` connects through iMCP's bundled `imcp-server` bridge (`@modelcontextprotocol/client`) and reports a status for Settings; `app/caller-id.js` follows the mic monitor

SceneViewCLAUDE.md

sceneview-android

SceneView/sceneview-android/CLAUDE.md

demo app per platform — `android-demo` is the Play Store app | | `mcp/` | `sceneview-mcp` server + packages | | `agents/` | Installable SceneView skills — a product surface, shipped to users | Full API reference: [`llms.txt

No other project uses it yet

hhyqhhReads credentialsCLAUDE.md

inno-agent

hhyqhh/inno-agent/CLAUDE.md

# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code

chernistryCLAUDE.md

bernstein

chernistry/bernstein/CLAUDE.md

system (pluggy) - `src/bernstein/plugins/` | | `tui/` | Textual TUI - `src/bernstein/tui/` | | `github_app/` | GitHub App integration - `src/bernstein/github_app/` | | `mcp/` | MCP server - `src/bernstein/mcp/` | | `benchmark/` | SWE-bench - `src/bernstein/benchmark/` | ## Directory context files Per-directory context files for agents

kgoedeckeCLAUDE.md

doop

kgoedecke/doop/CLAUDE.md

sandboxed iframes. People edit in the browser; AI agents edit through the built-in MCP server, streaming designs in live. Everyone sees cursors, presence, frame edits, agent status

greyhaven-aiReads credentialsCLAUDE.md

autocontext

greyhaven-ai/autocontext/CLAUDE.md

Agent runtime abstraction (Claude CLI, direct API) rlm/ # REPL-loop mode (optional analyst/architect) mcp/ # MCP server, tool implementations, sandbox manager server/ # FastAPI dashboard + WebSocket events tests/ # Pytest tests (~7700 tests

MicrosoftCLAUDE.md

skills-for-fabric

microsoft/skills-for-fabric/CLAUDE.md

Lakehouse data - XMLA/DAX for Semantic Models - KQL for Real-Time Intelligence ### Consumers - Use **MCP servers** for natural language queries - Limited to: Semantic Models, Warehouses, Lakehouse SQL Endpoints - No ODBC/JDBC setup

caliber-ai-orgCLAUDE.md

ai-setup

caliber-ai-org/ai-setup/CLAUDE.md

opencode/index.ts` · `github-copilot/index.ts` · `refresh.ts` · `staging.ts` · `backup.ts` · `manifest.ts` · `pre-commit-block.ts` **Scanner** (`src/scanner/`): `index.ts` — detects local MCP servers, rules, skills and enabled plugins across platforms **Sync** (`src/sync/`): `types.ts` · `adapters.ts` · `reconcile.ts` · `state.ts` · `frontmatter.ts

awdr74100CLAUDE.md

figwright

awdr74100/figwright/CLAUDE.md

commands, conventions, release flow, and gotchas. Claude Code specifics: - This repo **is** a Figma MCP server. The project-scoped `.mcp.json` launches the local build (`packages/mcp/dist/index.mjs`), so after changing `packages/mcp

huiliyi37Reads credentialsCLAUDE.md

Tianshu-harness

huiliyi37/Tianshu-harness/CLAUDE.md

playbook-store, trace-store └── Tool dispatch → API (SSE streaming) → TUI (纯 ANSI, src/tui/engine/) / Desktop (server SSE) ``` > ⚠️ 旧文档写「9 个固定 hook」是误导性简化。真相是条件装配，开关在 `loop-factory.ts:createRuntimeHooksPipeline` 传入的 deps。改 hook 行为前先看

electronicartsCLAUDE.md

gigi

electronicarts/gigi/CLAUDE.md

compilation and replaced with backend-specific code ### GigiMCP `GigiMCP/` is a Model Context Protocol (MCP) server that exposes GigiViewerDX12 functionality. It: - Implements JSON-RPC 2.0 over stdio - Connects to GigiViewerDX12

filamentphpCLAUDE.md

demo

filamentphp/demo/CLAUDE.md

important rather than explaining obvious details. === boost rules === # Laravel Boost - Laravel Boost is an MCP server that comes with powerful tools designed specifically for this application. Use them. ## Artisan

No other project uses it yet

jwuthri-cloudReads credentialsCLAUDE.md

Tracely-ai

jwuthri-cloud/Tracely-ai/CLAUDE.md

workers/` | Thin. Routers shape HTTP; tasks dispatch into a service. `api/mcp_server.py` mounts an MCP server at `/mcp` whose tools call those routers in-process over an ASGI transport (forwarding

Chorus-AIDLCCLAUDE.md

Chorus

Chorus-AIDLC/Chorus/CLAUDE.md

auth, prisma, api-response, uuid-resolver) ├── services/ # Business logic layer (all UUID-based) ├── mcp/ # MCP Server factory + permission-gated tool modules │ ├── server.ts # Creates per-auth MCP server instance │ └── tools/ # public.ts

No other project uses it yet

databuddy-analyticsReads credentialsCLAUDE.md

Databuddy

databuddy-analytics/Databuddy/CLAUDE.md

module for the SDK ui/ # Design system components (@databuddy/ui) ai/ # AI agent, query builders, MCP tools redis/ # Redis client, cacheable() caching, pub/sub, BullMQ queues, rate limiting shared/ # Shared types, utilities

No other project uses it yet

rusefiDeletes or force-pushesCLAUDE.md

rusefi

rusefi/rusefi/CLAUDE.md

# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code