Plan Mode

Plan Mode

Explore and analyze code safely without making any changes.

What Is Plan Mode?

Plan Mode is a read-only permission mode where Claude can explore your codebase, analyze code, and propose plans — but cannot write files, run commands, or make any changes. It is the safest way to get Claude's analysis.

How to Activate

Three ways to enter Plan Mode:

  • Shift + Tab — Cycle modes: default → acceptEdits → plan
  • Launch directly: claude --permission-mode plan
  • Prefix a single prompt with /plan to run just that turn in plan mode, then drop back

The Explore → Plan → Code Pattern

The most effective way to use Claude Code for non-trivial tasks:

1. Explore (Plan Mode)

Understand the codebase before touching anything:

text
/plan I need to add rate limiting to the API.
Explore @src/api/ and @src/middleware/.
What patterns are already used? Where should rate limiting go?

2. Plan (Still Plan Mode)

Ask Claude to produce a detailed implementation plan:

text
Based on what you found, create a step-by-step plan:
- which files to create/modify
- what tests to write
- what order to implement in
Don't implement yet.

3. Code (default / acceptEdits)

Approve the plan or Shift + Tab back to default / acceptEdits, then execute:

text
implement the rate limiting plan from above.
commit after each working step.

When to Use Plan Mode

  • Onboarding — Exploring a new codebase you just joined
  • Bug diagnosis — Tracing issues without accidentally changing code
  • Architecture review — Analyzing patterns, dependencies, and tech debt
  • Security audit — Scanning for vulnerabilities without modifying anything
  • Code review — Reviewing PRs with deep analysis

Tips

  • Use @ file references in Plan Mode — Claude can read any file you point to
  • Be specific about what analysis you need for complex architectural questions
  • When you approve a plan, Claude switches the session to the permission mode you picked (auto / acceptEdits / manual) and starts editing
  • Press Ctrl + G to open the proposed plan in your editor before approving
  • If you only need plan mode for one turn, prefix your prompt with /plan instead of switching modes

Why does 'plan before code' work so well?

The Explore → Plan → Execute loop is the fundamental pattern behind all autonomous agents. Understanding this architecture helps you work with any AI coding tool more effectively.

Learn the Agent Basics

Related Reading

  • Workflows — See Plan Mode in action in complete workflows
  • Cloud Workflows — Move large plans into Ultraplan
  • Dynamic Workflows — Turn broad plans into multi-agent workflow scripts
  • Debugging — Use Plan Mode for safe bug diagnosis
  • Hooks — Automate actions after planning

Continue with practice

You have finished the core ideas of Plan Mode.

If you want to turn the idea into something reusable, continue practicing on AgentWay.

Go to practice