How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
affaan-mCLAUDE.mdaffaan-m/ECC/CLAUDE.md
persistence, pre/post-tool hooks) - **rules/** - Always-follow guidelines (security, coding style, testing requirements) - **mcp-configs/** - MCP server configurations for external integrations - **scripts/** - Cross-platform Node.js utilities for hooks and setup - **tests
browser-useCLAUDE.mdbrowser-use/browser-use/CLAUDE.md
ruff format` - Pre-commit hooks: `uv run pre-commit run --all-files` **MCP Server Mode:** The library can run as an MCP server for integration with Claude Desktop: ```bash
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mcp/CLAUDE.md
mcp — the Caveman MCP server (commercial Go core + MIT launcher) A thin **stdio JSON-RPC** adapter exposing the compression [engine](../engine/CLAUDE.md) as five MCP tools to any host (Claude Code
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/mem/CLAUDE.md
bm25.go` — deterministic tokenizer + BM25 scorer (non-negative scores, so the threshold is meaningful). - `cmd/cavemem/` — MCP server + `remember`/`recall`/`supersede`/`history`/`forget` CLI subcommands (JSON). - `js/` + `py/` — thin TS and Python
JuliusBrusseeCLAUDE.mdJuliusBrussee/caveman/proxy/CLAUDE.md
silent no-op. `CAVE_SSRF_ALLOWLIST` opts loopback/private hosts back in (local model servers like Ollama; `localhost` as an entry covers 127.0.0.0/8 + ::1); metadata/link-local stay blocked in every mode
MicrosoftCLAUDE.mdmicrosoft/playwright/CLAUDE.md
fixtures | Test runner: reporters, config, annotations, retries | | `tests/mcp/` | `import { test, expect } from './fixtures'` | `client`, `server` | MCP tools via `client.callTool()` | **Decision rule**: Does the test need `browser`/`browserType`/`context` → `tests/library/`. Just
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/servers/CLAUDE.md
modelcontextprotocol/server-memory (knowledge graph persistence) sequentialthinking/ TS @modelcontextprotocol/server-sequential-thinking (step-by-step reasoning) fetch/ Py mcp-server-fetch (web content fetching) git/ Py mcp-server-git (git repository operations) time/ Py mcp
PanniantongCLAUDE.mdPanniantong/Agent-Reach/CLAUDE.md
youtube.py, etc.) - `agent_reach/channels/base.py` — Base channel class (all channels inherit from this) - `agent_reach/integrations/mcp_server.py` — MCP server integration - `agent_reach/skill/` — OpenClaw skill files - `agent_reach/guides/` — Usage guides - `tests/` — pytest tests - `config/mcporter.json
shanraisshanCLAUDE.mdshanraisshan/claude-code-best-practice/CLAUDE.md
subagent stops - `skills`: List of skill names to preload into agent context - `mcpServers`: MCP servers for this subagent (server names or inline configs) - `hooks`: Lifecycle hooks scoped to this subagent
danny-avilaCLAUDE.mddanny-avila/LibreChat/CLAUDE.md
instance. Test actual queries and schema validation, not mocked DB calls. - **MCP**: use real `@modelcontextprotocol/sdk` exports for servers, transports, and tool definitions. Mirror real scenarios, don't stub SDK internals
davila7CLAUDE.mddavila7/claude-code-templates/docs/CLAUDE.md
Serve locally with any static file server python -m http.server 8000 # or npx http-server # Open browser to http://localhost:8000 ``` ### Component Data Generation ```bash # From project root - regenerate components.json
tirth8205CLAUDE.mdtirth8205/code-review-graph/CLAUDE.md
graph forget PATH # drop files from the graph uv run code-review-graph serve # MCP server (stdio; --http for localhost) uv run code-review-graph wiki # Markdown wiki
nanocoaiCLAUDE.mdnanocoai/nanoclaw/container/CLAUDE.md
external account. Connecting GitHub or another app does not itself require a new MCP server. Use an existing HTTP client or the user's requested CLI, such as `gh`. Install
jarrodwattsCLAUDE.mdjarrodwatts/claude-hud/CLAUDE.md
line (`showTools`): ◐ Edit: auth.ts | ✓ Read ×3 - Skills/MCP lines (`showSkills` / `showMcp`): active Skill invocations and MCP servers; when the Skills line is enabled, Skill-tool entries are suppressed from the tools
alirezarezvaniCLAUDE.mdalirezarezvani/claude-skills/project-management/CLAUDE.md
grill-pm, /cs:pm-loop, /sprint-health, /project-health, /retro) **Key Feature:** Atlassian MCP Server integration for direct Jira/Confluence operations ## Orchestrator & Delivery Loop (pm-skills) `skills/pm-skills/` is the domain's `context: fork
SuperClaude-OrgCLAUDE.mdSuperClaude-Org/SuperClaude_Framework/CLAUDE.md
files) ├── skills/ # Installable skills (confidence-check, etc.) ├── hooks/ # Claude Code hook definitions ├── mcp/ # MCP server configurations (10 servers) └── core/ # Core utilities # Project Files tests/ # Python test suite (136 tests) ├── unit
microCLAUDE.mdmicro/go-micro/CLAUDE.md
RabbitMQ) ├── cache/ # Caching (Redis) ├── client/ # RPC client (gRPC) ├── cmd/micro/ # CLI tool (run, deploy, mcp, build, server) ├── codec/ # Message codecs (JSON, Proto) ├── config/ # Dynamic config (env, file, etcd, NATS) ├── errors/ # Error
czlonkowskiCLAUDE.mdczlonkowski/n8n-mcp/CLAUDE.md
typecheck # tsc --noEmit (npm run lint is an alias) # Running the server npm start # MCP server in stdio mode npm run start:http # MCP server in HTTP mode
teng-linCLAUDE.mdteng-lin/notebooklm-py/CLAUDE.md
requires auth) uv run notebooklm --help # CLI ``` Always install the full extras set (`mcp`, `server`, `impersonate`); omitting them causes adapter suites to skip silently, masking errors and failing
getpaseoCLAUDE.mdgetpaseo/paseo/CLAUDE.md
Repository map This is an npm workspace monorepo: - `packages/server` — Daemon: agent lifecycle, WebSocket API, MCP server - `packages/app` — Mobile + web client (Expo) - `packages/cli` — Docker-style CLI (`paseo run/ls/logs/wait`) - `packages/relay` — E2E encrypted
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.
