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.
DatabricksCLAUDE.mddatabricks/app-templates/mcp-server-hello-world/Claude.md
This file provides context about this project for AI assistants like Claude. This is a Model Context Protocol (MCP) server template built with FastMCP and FastAPI, designed to run as…
DatabricksCLAUDE.mddatabricks/app-templates/mcp-server-open-api-spec/CLAUDE.MD
This document provides architectural context and implementation details for the Custom OpenAPI Spec MCP Server project. It's designed to help AI assistants understand the codebase structure, patterns, and conventions. This…
DatabricksCLAUDE.mddatabricks/app-templates/vacation-rentals/CLAUDE.md
This project uses Databricks AppKit packages. For AI assistant guidance on using these packages, refer to: For enhanced AI assistance with Databricks CLI operations, authentication, data exploration, and app development,…
AnthropicCLAUDE.mdanthropics/claude-code-playground/CLAUDE.md
This repository is destined to be public. Treat every file as if it were already published.
MicrosoftCLAUDE.mdmicrosoft/Agents-for-python/CLAUDE.md
This is the Microsoft 365 Agents SDK for Python, a framework for building enterprise-grade conversational agents for M365, Teams, Copilot Studio, and other platforms. The SDK replaces the legacy Bot Framework SDK (botbuilder packages) with a modern, modular architecture. Important: Python imports use underscores (microsoft_agents), not dots (microsoft.agents). Quick setup (Linux/macOS): Quick setup (Windows): Manual setup (from repository root): Python version: Requires Python 3.10+, supports 3.10-3.14. Recommended: Python 3.11+ The SDK follows a layered, modular architecture with clear separation of…
Hugging FaceCLAUDE.mdhuggingface/leLab/CLAUDE.md
LeLab is a FastAPI + React web interface wrapping the LeRobot framework for the SO-101 leader/follower arm. It exposes teleoperation, dataset recording, calibration, replay, and training as HTTP/WebSocket endpoints, replacing LeRobot's CLI + keyboard-driven flows. The frontend (React + Vite) lives in frontend/. The bundle in frontend/dist/ is not committed: setup.py builds it while building the wheel, with Node from the nodejs-wheel-binaries build requirement, and ships it as package data (frontend.__init__.py makes setuptools treat it as a package); lelab/server.py mounts…
JetBrainsCLAUDE.mdJetBrains/psiviewer/CLAUDE.md
IntelliJ Platform plugin: a tool window that shows the PSI (Program Structure Interface) tree of the current file/element, plus a property sheet for the selected node. Aimed at plugin developers.…
JetBrainsCLAUDE.mdJetBrains/kotlin-desktop-toolkit/CLAUDE.md
AGENTS.md is the canonical agent guide — build/test/lint commands, the Kotlin↔Rust split, the Win32 doc-set pointer, and platform scope live there. This file only adds Claude-Code-specific notes.
AWSReads credentialsCLAUDE.mdawslabs/loom/CLAUDE.md
No summary in the file. Open it to read it.
MongoDBCLAUDE.mdmongodb/mongodb-atlas-kubernetes/CLAUDE.md
MongoDB Atlas Kubernetes Operator — a Kubernetes operator that provides native integration between Kubernetes and MongoDB Atlas. It manages Atlas projects, clusters, database users, network access, backups, and more through Kubernetes custom resources. This project uses devbox. Before making any changes, verify you are inside a devbox environment: If not in a devbox environment, always ask the user whether to prefix commands with devbox run. Code style and formatting conventions are maintained as agent skills. See the Skills section below…
PostHogCLAUDE.mdPostHog/wizard/CLAUDE.md
Repo guidance for all agents lives in AGENTS.md — the single source of truth. It's imported below so Claude Code picks it up automatically.
NVIDIACLAUDE.mdNVIDIA/topograph/.claude/CLAUDE.md
This file is the short core. It carries the invariants an agent must not break, the boundaries of what an agent may change on its own, and the conventions that are specific to this codebase. Everything else lives in the document that already owns it and is not repeated here: When you change behaviour that one of those documents describes, update that document. Do not answer the same question here as well; two copies of a rule drift apart, and…
MicrosoftCLAUDE.mdmicrosoft/playwright.dev/CLAUDE.md
Semantic commit messages: label(scope): description Labels: fix, feat, chore, docs, test, devops Never add Co-Authored-By agents in commit message. Branch naming for issue fixes: fix-<issue-number>
JetBrainsCLAUDE.mdJetBrains/pest-intellij/CLAUDE.md
Prefer MockK to other mocking approaches. When using MockK, prefer explicit stubbing over inline lambda syntax:
PostHogReads credentialsCLAUDE.mdPostHog/duckgres/CLAUDE.md
This file provides context for Claude Code sessions working on this codebase. Duckgres is a PostgreSQL wire protocol server backed by DuckDB. It allows any PostgreSQL client (psql, pgAdmin, lib/pq, psycopg2, JDBC, etc.) to connect and execute queries against DuckDB databases. Duckgres has three deployment topologies, built from three primary run modes (standalone, control-plane, duckdb-service; a fourth utility mode, reshard-runner, is the entrypoint of the dedicated per-operation reshard pods the control plane spawns — see the Resharding section): 1. Standalone…
PostHogCLAUDE.mdPostHog/duckgres/scripts/client-compat/CLAUDE.md
Docker Compose-based test framework that runs real PostgreSQL client libraries against duckgres and collects results into a DuckDB database. Lives under scripts/client-compat/. Key design point: the gatherer does NOT track which clients are done. The justfile handles all lifecycle coordination via docker wait. This avoids hangs when clients crash before reporting. Clients report results via HTTP to $RESULTS_URL (defaults to http://results-gatherer:8080): All reporting is fire-and-forget (errors silently swallowed) so clients also work standalone without the gatherer. Use report_client.py (copied into…
MicrosoftCLAUDE.mdmicrosoft/Agents-for-net/CLAUDE.md
See .github/copilot-instructions.md for build commands, architecture, conventions, and coding guidelines for this repository.
AWSCLAUDE.mdawslabs/amazon-dynamodb-tools/tools/bulk_executor/.claude/CLAUDE.md
After completing a logical set of changes, run the unit tests to verify nothing is broken. All python commands must activate the local virtual environment first. From the tools/bulk_executor/ directory:
SentryCLAUDE.mdgetsentry/sentry-unreal/CLAUDE.md
This project is the Sentry SDK for Unreal Engine which provides crash and error monitoring as well as performance tracking for games built with Unreal Engine. It wraps multiple Sentry SDKs for supported platforms (sentry-native for Windows/Linux/macOS/Xbox/WinGDK/PlayStation/Nintendo, sentry-cocoa for macOS/iOS, sentry-java for Android) into a single Unreal Engine plugin and extends them with Unreal Engine-specific functionality. For sentry-native platforms SDK supports multiple crash handler backends. The backend is selected in Sentry.Build.cs at build time via the UseNativeBackend setting configured in…
MicrosoftCLAUDE.mdmicrosoft/fabric-cli/.ai-assets/context/CLAUDE.md
Context for Claude Code helping users work with the Fabric CLI. Copy or symlink to CLAUDE.md or .claude/CLAUDE.md. Fabric CLI (fab) is a command-line tool for Microsoft Fabric with interactive (REPL) and command-line modes. Filesystem-like hierarchy with dot entity suffixes: Switch: fab config set mode interactive or fab config set mode cli Dot-prefixed, not shown by default. Use ls -a to view. Config files in ~/.config/fab/: - cache.bin - encrypted token cache - config.json - CLI settings - auth.json -…
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.
