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
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.
