Plan mode
A coding agent mode in which it can read code and run safe commands but not edit files, and ends with a plan for you to approve.
In plan mode the agent explores the repository, asks questions and writes a plan; nothing changes on disk until you approve. In Claude Code it is one of the permission modes, switched with Shift+Tab or started with --permission-mode plan; other coding agents have similar modes. It is the human-approved form of plan and execute.
Reviewing a plan is much cheaper than reviewing a diff: a wrong file, a wrong approach or a missing requirement is visible in a few lines. That is why it is the first step of research, plan, implement and a natural place for a human in the loop. For small, obvious changes it only adds friction.
Sources
- Claude Code Docs: Choose a permission mode code.claude.com
Related terms
- Research, plan, implement (RPI): Working with a coding agent in three phases, each in a fresh context: research the code into a document, write a plan from it, then implement the plan.
- Agent permission modes (YOLO mode): Settings that decide what a coding agent may do without asking, from approving every command to skipping all checks, known as YOLO mode.
- Plan-and-execute: A planner model writes a step-by-step plan, executor models carry out the steps, and the planner revises the plan when a step fails.
- Human in the loop: A person approves, edits or rejects the agent’s action before it takes effect.
- Coding agent: An agent that reads a repository, edits files, runs commands and tests, and opens pull requests.
