# The Best Setup for the .claude Folder for Maximum Efficiency

> The .claude folder gives Claude Code a hierarchical config that optimizes token usage through modular rules, skills, and deterministic hooks.

Source: https://camnangai.com/en/for/developers/claude-folder-setup  
Published: 2026-07-23

The **.claude folder** is the primary configuration entry point for managing [Claude Code](https://camnangai.com/en/tools/what-is-claude-code)'s behavior within a repository. Efficient project management requires a hierarchical configuration structure that prioritizes low token overhead and high instruction adherence.

A high-performance setup uses a multi-layered approach: a lean, memoized root `CLAUDE.md` for baseline context, path-scoped rules for modularity, skills for on-demand workflows, and a `settings.json` for deterministic tool control. By separating instructions based on frequency of access and technical concern, you optimize the context window for actual development tasks.

Well-structured configurations prevent context drift during long-running sessions. By loading specific instructions only when they are relevant to the active file path, you minimize the risk of the model ignoring critical constraints or spending compute on irrelevant data.

![Diagram of the .claude folder as a layered control center: CLAUDE.md, rules, commands, skills, agents and settings.json around the Claude Code core](https://camnangai.com/articles/thiet-lap-thu-muc-claude/01-infographic-en.webp)

## Two .claude folders: project scope and global scope

You manage two distinct `.claude` directories to balance team standards with personal environment needs. The project-level `.claude/` directory, located in the repository root, should be committed to Git to ensure consistent behavior across the engineering team. The global `~/.claude/` directory (at `%USERPROFILE%\.claude` on Windows) manages personal state, including session history and machine-specific auto-memory.

![Comparison of the two .claude directories: the project folder committed to Git for the team, and the global ~/.claude folder for personal config](https://camnangai.com/articles/thiet-lap-thu-muc-claude/02-en.webp)

Claude Code resolves settings through a strict precedence cascade. Higher-priority levels override lower-priority configurations.

| Priority    | Source           | Location                                             |
| :---------- | :--------------- | :--------------------------------------------------- |
| 1 (Highest) | Managed Policy   | System-level (deployed via MDM or config management) |
| 2           | CLI Arguments    | Command-line flags passed at invocation              |
| 3           | Local Overrides  | `.claude/settings.local.json`                        |
| 4           | Project Settings | `.claude/settings.json`                              |
| 5 (Lowest)  | User Settings    | `~/.claude/settings.json`                            |

For project-specific preferences that should not be shared — debug flags, local paths — use `.local` files. `CLAUDE.local.md` and `settings.local.json` are automatically ignored by the Claude Code Git integration, so personal overrides never pollute the shared repository.

## CLAUDE.md — the foundation file, keep it under 200 lines

`CLAUDE.md` is the initial context for every session. It is memoized — read once and cached for the duration of the session — and the cache is only cleared and re-read after a conversation compaction. Include high-level technical data here: build and test commands, tech-stack specifics, core architecture decisions, and the critical "gotchas" Claude can't infer from code.

Strictly hold to a 200-line limit. Excessive length increases token costs and causes
the model to ignore instructions. If the file grows past this limit, migrate specific conventions
into path-scoped rules.

Root files load at startup. Subdirectory `CLAUDE.md` files (e.g. `src/api/CLAUDE.md`) load on demand when Claude accesses files within that path. In monorepos, this ensures teams only consume tokens for their own modules.

```markdown
# Project: Analytics API

## Commands

- Build: docker-compose build
- Test: pytest
- Lint: ruff check .

## Architecture

- FastAPI with SQLAlchemy (PostgreSQL)
- Business logic lives in app/services/
- Schemas use Pydantic v2 in app/schemas/

## Conventions

- Use file-scoped dependencies for Auth
- Async methods must use the Async suffix
- Return types must use the ApiResponse wrapper
```

_The rest of this article is for members. Read it at https://camnangai.com/en/for/developers/claude-folder-setup_