plan-mode
5 questions
- AI
How do I run my first Claude Code session?
Open Claude inside a real repo, ask one concrete task, read the diff before approving, and use /clear when context drifts. Most beginner pain comes from overstuffed CLAUDE.md, mixed-task sessions, and rubber-stamping edits.
- AI
How do I make Claude plan before it edits code?
Press Shift+Tab in the CLI until the input shows plan mode, or write 'do not edit yet, write a plan'. Plan mode holds source edits until you approve; reads and shell commands still run (with normal prompts). Approve only plans that list exact files, an explicit out-of-scope list, and a verification command.
- AI
When you ask Claude to execute a plan, how faithfully does the implementation track it?
A captured `claude --print` session that executes the 196-line plan from scenario #33. The prompt anchored Claude to the plan: 'do not deviate; if the plan is wrong, fix the plan in a comment in the test file rather than changing the structure.' Claude implemented exactly to spec for everything except one genuine plan defect (a `mockReturnValueOnce` that would have silently failed because `markFailed` calls `now()` twice), which it surfaced as a six-line `PLAN-FIX` comment instead of silently fixing. The article shows the 16-tool-call execution sequence, the parts that stuck, the one deviation, and what that workflow buys you over straight implementation.
- AI
What does Claude Code's plan mode actually produce on a real refactor?
A captured `claude --print --permission-mode plan` session that asked Claude to add a retry mechanism with exponential backoff and a dead-letter queue to the demo's notifications service. Plan mode redirects Claude to read, explore, and write a plan to `~/.claude/plans/`, with no project edits. The output was a 196-line specification with a decision table, state machine, file list, 23 enumerated test cases, and a backwards-compatibility note. The article shows what plan mode produces, what it skips, and when the plan beats the implementation as the deliverable.
- AI
How do I start a plan locally, work on it remotely, and finish in my terminal?
Type /ultraplan in a Claude Code v2.1.91+ session to hand the planning task to a Claude Code on the web cloud session running in plan mode. The CLI shows a status indicator while you work; when the plan is ready, choose to execute in the cloud or teleport back to your terminal.