How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
patrickchughCLAUDE.mdpatrickchugh/terravision/docs/CLAUDE.md
/v1/chat/completions # Export graph data poetry run terravision graphdata --source --outfile architecture.tvg.json # Run as an MCP server for AI agents (needs the optional [mcp] extra) poetry run terravision mcp --output
ddalcuCLAUDE.mdddalcu/mlx-serve/app/CLAUDE.md
pair with calls by INDEX. Per-tool headlines are a LIST, not a rule; MCP `server__tool` shows as `server/tool` via `MCPManager.parseNamespacedName`. Guards: `ToolCallDisplayTests`, `ChatRowBuilderTests`. - **A background handle
Asymptote-LabsCLAUDE.mdAsymptote-Labs/agent-beacon/CLAUDE.md
recorded as `command.executed`, carry Python status/output metadata, and have no invented exit code. MCP is not separately attributed because Prime exposes integrations inside the kernel. `beacon endpoint prime sync
AminForouCLAUDE.mdAminForou/mcp-gsc/CLAUDE.md
coding assistants (Claude, Cursor, Copilot, etc.) working in this repo. ## What this is MCP server that connects Google Search Console to AI assistants. Single file: `gsc_server.py` (~1,670 lines). Built
actionbookCLAUDE.mdactionbook/actionbook/CLAUDE.md
Module Structure ``` actionbook/ ├── packages/ │ ├── js-sdk/ # @actionbookdev/sdk - JavaScript SDK with tool definitions │ ├── mcp/ # @actionbookdev/mcp - MCP Server (standalone, publishable to npm) │ ├── cli/ # @actionbookdev/cli - Command line interface (Rust CLI + npm wrapper) │ └── tools
DockerCLAUDE.mddocker/mcp-gateway/CLAUDE.md
Gateway** - a CLI plugin that enables easy and secure running of Model Context Protocol (MCP) servers through Docker containers. The plugin acts as a gateway between AI clients and containerized
svnschaCLAUDE.mdsvnscha/mcp-windbg/CLAUDE.md
main(): CLI argument parsing, picks the transport __main__.py module entry point server.py MCP server: tool param models + list_tools + call_tool dispatch cdb_session.py CDBSession: spawns cdb.exe, sends commands, reads
rivet-devCLAUDE.mdrivet-dev/sandbox-agent/examples/CLAUDE.md
host directories into Docker example containers. - If an example needs tools, skills, or MCP servers, install them inside the container during setup. ## Testing Examples (ACP v2) Examples should be validated
rivet-devCLAUDE.mdrivet-dev/sandbox-agent/foundry/CLAUDE.md
changes, restart the backend container: `just foundry-dev-down && just foundry-dev`. - The dev server has debug logging enabled by default (`RIVET_LOG_LEVEL=debug`, `FOUNDRY_LOG_LEVEL=debug
CopilotKitCLAUDE.mdCopilotKit/OpenGenerativeUI/CLAUDE.md
port 3000 pnpm dev:agent # LangGraph agent on port 8123 pnpm dev:mcp # MCP server # Build all apps pnpm build # Lint all apps pnpm lint ``` ### Environment Setup ```bash # Set Anthropic
fynnflueggeCLAUDE.mdfynnfluegge/agtx/CLAUDE.md
current project's config (enables its scripts and copy_files) ./target/release/agtx trust # Run the MCP server (global mode, or project-scoped with a path) ./target/release/agtx mcp-serve [path] # Serve
silversteinCLAUDE.mdsilverstein/minutes/CLAUDE.md
appropriate app bundle - TCC-sensitive desktop work (hotkeys, Screen Recording, Input Monitoring, Accessibility): `./scripts/install-dev-app.sh` - MCP server changes: `cd crates/mcp && npm run build` (compiles TS server + builds UI, then restart MCP
Open-Source-LegalCLAUDE.mdOpen-Source-Legal/OpenContracts/CLAUDE.md
commit hooks) pre-commit run --all-files ``` ### Frontend (React/TypeScript) ```bash cd frontend # Start development server (proxies to Django on :8000) yarn start # Run unit tests (Vitest) - watches by default yarn
ghostwrightCLAUDE.mdghostwright/phantom/CLAUDE.md
validated self-evolution engine, communicates via Slack/Web Chat/Telegram/Email/Webhook, and exposes all capabilities as an MCP server. 30,000+ lines of TypeScript, 1,819 tests, v0.20.2. Apache 2.0, repo at ghostwright/phantom
JetBrainsCLAUDE.mdJetBrains/compose-hot-reload/CLAUDE.md
invalidated after reload | | `hot-reload-devtools` | Developer tools UI window | | `hot-reload-mcp` | MCP server for AI agent integration | | `hot-reload-test` | Test infrastructure and test plugins | | `tests/` | Functional integration
JwuthriCLAUDE.mdJwuthri/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
yohey-wCLAUDE.mdyohey-w/multi-agent-shogun/CLAUDE.md
Claude Code + tmux multi-agent parallel dev platform with sengoku military hierarchy
Prismer-AICLAUDE.mdPrismer-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
m0n0x41dCLAUDE.mdm0n0x41d/haft/CLAUDE.md
coding agent (Claude Code, Codex, OpenCode, Cursor), this CLI for manual access, and the MCP server (`haft serve`) for programmatic access. Standalone interactive agent (`haft agent`), TUI, and desktop wrappers
mbaileyCLAUDE.mdmbailey/voicemode/CLAUDE.md
SemVer. 4. `make release`, then watch the Actions run. ## Architecture Overview ### Core Components 1. **MCP Server (`voice_mode/server.py`)** - FastMCP-based server providing voice tools via stdio transport - Auto-imports
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.
