How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
AnthropicCLAUDE.mdanthropics/launch-your-agent/CLAUDE.md
patterns + typical endpoint schemas — so v1 is just the swap to the real MCP server + vault. - **Voice**: warm welcome, no clinical process talk, no time estimates or unverified durations; compact/dense
hoangsonwwCLAUDE.mdhoangsonww/Claude-Code-Agent-Monitor/CLAUDE.md
printed command, surfaced in the UI and by `ccam update-check`.) - `mcp/`: local MCP server exposing dashboard operations as tools. ## Non-negotiable engineering rules - Preserve existing behavior unless explicitly asked
bytechefhqCLAUDE.mdbytechefhq/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
MadAppGangCLAUDE.mdMadAppGang/claudish/CLAUDE.md
write | Means | |---|---|---| | harness | host | Claude Code driving the session; "host" is the MCP host that spawns the server | | foreign model | external model | any model not native to the harness
jarrodwattsCLAUDE.mdjarrodwatts/claude-delegator/CLAUDE.md
uninstall to test removal flow /claude-delegator:uninstall ``` No build step, no dependencies. Uses native MCP servers from Codex and Gemini CLIs. ## Architecture ### Orchestration Flow Claude acts as orchestrator—delegates
shanraisshanCLAUDE.mdshanraisshan/codex-cli-best-practice/CLAUDE.md
Config** (`.codex/config.toml`) — TOML-based layered config with 5 profiles (conservative, development, trusted, ci, review), MCP server registration, and agent definitions. Project-level overrides user-level (`~/.codex/config.toml`); CLI flags override both
Pantheon-SecurityCLAUDE.mdPantheon-Security/medusa/CLAUDE.md
Security MEDUSA scans with 40,000+ built-in patterns for: - AI/ML applications, LLM agents, MCP servers - Prompt injection, RAG poisoning, agent security - Traditional vulnerabilities (SQL injection, XSS, secrets) - Configuration files
zeenie-aiCLAUDE.mdzeenie-ai/OpenCompany/CLAUDE.md
# OpenCompany - Claude Documentation ## Project Overview This is a React Flow-based workflow automation platform
rohitg00CLAUDE.mdrohitg00/kubectl-mcp-server/CLAUDE.md
kubectl-mcp-server Project Memory ## Project Overview - **Name**: kubectl-mcp-server - **Version**: 1.22.0 - **Description**: A Model Context Protocol (MCP) server for Kubernetes with 270+ tools, 8 resources, and 8 prompts
agentic-communityCLAUDE.mdagentic-community/mcp-gateway-registry/CLAUDE.md
MongoDB is running** (for integration tests): ```bash docker ps | grep mongo # Should show: mcp-mongodb running on 0.0.0.0:27017 ``` 2. **Test environment is configured**: - Tests automatically set `DOCUMENTDB_HOST=localhost
MicrosoftCLAUDE.mdmicrosoft/power-platform-skills/plugins/power-automate/CLAUDE.md
environments`, `setup`) - `references/` — shared docs referenced by skills via `../../references/…` - `.mcp.json` — launches the FlowAgent MCP server (registered as `flowagent`) ## Engine vs plugin This folder is the **plugin**: skills, references, MCP
kossakovskyCLAUDE.mdkossakovsky/selfhost-ai/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
apifyCLAUDE.mdapify/mcpc/CLAUDE.md
commands for shell access, scripts, and AI coding agents. `mcpc` can connect to any MCP server over Streamable HTTP or stdio transports, securely login via OAuth credentials and store credentials
QuantGeekDevCLAUDE.mdQuantGeekDev/mcp-framework/CLAUDE.md
repository. ## Project Overview mcp-framework is a TypeScript framework for building Model Context Protocol (MCP) servers. It provides an opinionated architecture with automatic directory-based discovery for tools, resources
opentabs-devCLAUDE.mdopentabs-dev/opentabs/.agents/skills/build-plugin/CLAUDE.md
content from the previously separate plugin-icon, troubleshoot, setup-plugin skills and the former MCP server prompts/resources
opentabs-devCLAUDE.mdopentabs-dev/opentabs/CLAUDE.md
Project Instructions for Claude ## Project Overview **OpenTabs Platform** is a Chrome extension + MCP server with a plugin-based architecture. A plugin SDK allows anyone to create OpenTabs plugins as standalone
opentabs-devCLAUDE.mdopentabs-dev/opentabs/e2e/CLAUDE.md
Test Instructions ## Overview Playwright E2E tests that exercise the full stack: MCP server + Chrome extension + test web server + test plugin. Tests run under Playwright's Node.js test runner, so Node.js
opentabs-devCLAUDE.mdopentabs-dev/opentabs/plugins/CLAUDE.md
dist/tools.json`, auto-registers the plugin in `localPlugins`, and calls `POST /reload` to notify the MCP server) ## Plugin Icons Place an `icon.svg` file in the plugin root directory. The build tool
opentabs-devCLAUDE.mdopentabs-dev/opentabs/.ralph/CLAUDE.md
During E2E, each Playwright worker (2 per container, via `CI=1`) spawns an MCP server, a test server, and a Chromium instance (~600 MB each), totaling ~1.5 GB for Playwright
awdr74100CLAUDE.mdawdr74100/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
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.
