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.
- #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.mdat 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.mdis 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>.mddefines 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
Keep reading
More guides like this one.
What to Actually Install in Claude (and the Order)
The full menu — eight plugins, eight skills, eight MCP servers — worth adding to Claude, each with the command to install it, who it's for, and the four-week order to add them so you build a stack you use, not a museum of installs.
Claude Code for Engineers — From Chat to Coworker
Most engineers use Claude like a smarter search box. Here is the short path to using it like a teammate that actually ships work on your machine.
Loop Engineering: When You Stop Prompting and Start Managing
The Head of Claude Code says he doesn't prompt anymore — loops prompt for him. Here's what a loop actually is, the pieces that make one, and how to build your first without writing code.