renderer at a site. NEVER use
`mcp__claude-in-chrome__*` tools — they are slow, unreliable, and not what this
project uses.
**Server / sidebar / extension internals:** before editing `browse/src/server.ts`,
`extension
ruff format`
- Pre-commit hooks: `uv run pre-commit run --all-files`
**MCPServer Mode:**
The library can run as an MCPserver for integration with Claude Desktop:
```bash
mcp — the Caveman MCPserver (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
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.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
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.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.