learnaiwithrafa
ClaudeSetup

The 7 Levels of Claude Code — Find Yours, Climb One

Most engineers stall at level 3, treating Claude Code like a smarter terminal. Here's the ladder from chat to agent teams — find your rung and do the one step that moves you up.

3 min read2 sources
  • #claude-code
  • #setup
  • #agents

I run engineering at a US startup, and the gap between people who get real leverage from Claude Code and people who don't isn't talent — it's which rung they're stuck on. Most stall at level 3. Here's the ladder. Find where you are, then take the single setup step that lifts you a rung. Install first if you haven't: curl -fsSL https://claude.ai/install.sh | bash, then cd your-project && claude.

The ladder

  • Level 1 — Prompting. You type, it answers. Claude as a smarter search box. claude "write tests for the auth module and fix them until they pass" is still level 1 if you babysit every step.
  • Level 2 — Context. A CLAUDE.md at your project root, read at the start of every session, so you stop re-explaining your stack. This is the highest-payoff ten minutes in the whole ladder.
  • Level 3 — Tools. On your machine, Claude opens files, creates new ones, executes commands, and runs its own web searches — no copy-paste. It does instead of suggests. Most people camp here.
  • Level 4 — MCP. Level 3 gave it hands on your machine; MCP gives it keys to everything else. claude mcp add --transport http <name> <url>, or commit a project .mcp.json. Start with the one tool you touch daily.
  • Level 5 — Skills. A .claude/skills/<name>/SKILL.md is a playbook Claude loads automatically when the task matches. Only the description is scanned at startup, so it costs nothing until it fires. Anthropic's team lives by one rule here: repeat a task even twice in a day, and it should be a skill.
  • Level 6 — Subagents. A .claude/agents/<name>.md defines a specialized worker with its own context and tool permissions — a read-only reviewer is the best first one. Add "use subagents" to a big task and Claude splits the work across parallel workers.
  • Level 7 — Agent teams. Multiple full Claude sessions coordinating on shared work, each in an isolated worktree. This is where "using AI" becomes "managing an AI team." Almost nobody's here yet — and you don't need it for most work.

The habit that pays off later

Whenever Claude gets something wrong, close the correction with: "note this in CLAUDE.md so it never happens again." Two weeks of that and it stops repeating your specific mistakes. The skills that matter at level 7 — clear specs, good context hygiene, verification habits — are the ones you build climbing the lower rungs.

Do this today

Find your rung honestly, then do its one step. If you're at level 1 or 2, write a one-page CLAUDE.md for your most active repo. Climbing one level a week puts you ahead of nearly every engineer you work with by next month.

Sources