n8n-install
kossakovsky/n8n-install/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
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.
kossakovsky/n8n-install/CLAUDE.md
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code
getsentry/sentry-mcp/packages/mcp-core/src/internal/agents/tools/data/CLAUDE.md
protocols) - **server** - Server-side operations (addresses, ports) - **service** - Service identification (name, version, instance) - **error** - Error information (type, message, stack) - **user** - User identification (id, email, name) - **mcp** - Model Context Protocol attributes
Apicurio/apicurio-registry/CLAUDE.md
then add the matching symlink under `.opencode/`. ## MCP Integration The `mcp/` module provides an MCP server. Connect Claude Code to a running registry instance for live artifact and schema management
GarethManning/claude-education-skills/CLAUDE.md
Python (16.7%). Playwright for testing. Skills are structured markdown (SKILL.md) with YAML frontmatter. MCP server in mcp-server/ subdirectory. CI via GitHub Actions. ## Test `npx playwright test` ## Read at session
homeassistant-ai/skills/evals/CLAUDE.md
model. Set `--ctx-limit` just under the loaded context: some servers crash on overflow instead of erroring. Its ha-mcp texts are copied from `server.py` at the commit its docstring
QuantGeekDev/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
krafton-ai/KIRA/KIRA-Slack/CLAUDE.md
agents/proactive_dynamic_suggester/` | | **Proactive Confirm** | Haiku | ✅ | Request suggestion approval | `cc_agents/proactive_confirm/` | --- ## 🛠️ MCP Tools Available ### Core MCP Servers - **slack**: 11 tools (messages, files, reactions, channel management, etc.) - **outlook**: 7 tools (email query, compose
Auties00/Cobalt/CLAUDE.md
stanza dist/index.js`); they are NOT part of the Maven build. | Tool | Purpose | |--------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | `tools/web/mcp-server` | MCP server exposing the WA Web RE surface used during development: module/export search, dependency graphs, WASM analysis
microsoft/fabric-toolbox/tools/MicrosoftFabricMgmtMCPServer/CLAUDE.md
CLAUDE.md — MicrosoftFabricMgmt MCP Server Development Guide ## Overview This directory contains a Python-based **Model Context Protocol (MCP) server** that wraps the [MicrosoftFabricMgmt PowerShell module](../MicrosoftFabricMgmt/) and exposes its capabilities
opentabs-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-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-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-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-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
jdevalk/specification.website/CLAUDE.md
marketing. For any MDN link or browser-support claim, resolve it through the **MDN MCP server** (`https://mcp.mdn.mozilla.net/`, free, no auth) — it returns the current canonical URL (MDN reorganises
rush86999/atom/CLAUDE.md
register_server` (real handshake, replaces the placeholder), `api/mcp_client_routes.py` (`/api/mcp/servers`): Atom connects to arbitrary external MCP servers (Cloudflare "MCP Server Portals"), not just the 3 hardcoded pseudo-servers. 48. **Per-Canvas
pnp/powershell/CLAUDE.md
adding one. - **Skills**: `.claude/skills/` — `code-review`, `new-cmdlet`. Same arrangement. - **MCP**: `.mcp.json` configures the GitHub and Microsoft Learn servers. See [`.agents/README.md`](.agents/README.md). `docs-sync`, `permissions-auditor` and `api-surface-diff
pocketpaw/pocketpaw/CLAUDE.md
buffering with edit-in-place (1.5s rate limit). Auto-registers a `pocketpaw-discord` MCP server on startup exposing Discord operations to all MCP-capable backends. Admin commands (`/converse`, `/setstatus
ComposioHQ/trustclaw/CLAUDE.md
shadcn MCP** tools instead. ## Architecture This dashboard uses a **single tRPC backend** running within Next.js. Auth is handled by Better Auth with username/password. Composio functionality is accessed server-side using
ecubus/EcuBus-Pro/CLAUDE.md
Commit Rules - Do NOT add `Co-authored-by` trailers to commit messages. ## MCP Servers Workspace MCP config in `.vscode/mcp.json`. The `playwright` server (`npx -y @playwright/mcp@latest`) is useful for browser
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.