Answer: For big tasks, press Shift+Tab twice to cycle into plan mode (the first press enters acceptEdits) and ask Claude to plan without changing anything, then review and adjust the plan before switching modes and saying "do step 1." Between separate tasks, run /clear to start fresh, since your CLAUDE.md carries the durable context forward. Status: Confirmed Entry: tool/claude-apps/features/plan-mode-and-clear-prompting Revision: 1 Digest: sha256:85b24dd6f9366727 (changes whenever the content changes) Timeline: Created: 2026-11-13T02:59:34Z Last changed: 2026-11-13T02:59:34Z Last verified: 2026-11-20T12:06:44Z Next check: 2026-11-21T12:06:44Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Plan Mode shortcut | Shift+Tab twice | [1] | 2026-11-20 Plan Mode example prompt | Plan how you'd add rate limiting to the public API. Don't change anything yet. | [1] | 2026-11-20 Next step after plan | do step 1 | [1] | 2026-11-20 Clear command | /clear | [1] | 2026-11-20 Context carried forward | CLAUDE.md | [1] | 2026-11-20 Sources: [1] Anthropic. "Give Claude context: CLAUDE.md and better prompts | Claude Help Center". https://support.claude.com/en/articles/14553240-give-claude-context-claude-md-and-better-prompts Role: primary. Accessed: 2026-11-20T12:06:44Z Quote: "press Shift+Tab twice to cycle into plan mode (the first press enters acceptEdits)" (Supports: Plan Mode shortcut) Quote: "Plan how you'd add rate limiting to the public API. Don't change anything yet." (Supports: Plan Mode example prompt) Quote: "switch modes and say "do step 1."" (Supports: Next step after plan) Quote: "One task per conversation; /clear between them" (Supports: Clear command) Quote: "Your CLAUDE.md carries the durable context forward, so the chat history does not need to." (Supports: Context carried forward) Snapshot SHA-256: 4ec3a0367514f796ce185c88841ff00cd0febd3266196da4b8284eabe19c8c13 (captured 2026-11-13T02:59:33Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T02:59:34Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:06:44Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:06:44Z Last attempt: 2026-11-20T12:06:44Z Notes and limitations: Extracted automatically from a single official source (section "Part 2 — Prompting habits that pay off in Claude Code"). Related: https://latestn.com/tool/claude-apps/features/projects-after-move What happens to my Claude Design projects and chats after moving to Claude? https://latestn.com/tool/claude-apps/features/record-a-skill How do I record a skill in Claude and what is kept from the recording? https://latestn.com/tool/claude-apps/features/research-with-extended-thinking Can I use research and extended thinking together in Claude? https://latestn.com/tool/claude-apps/features/package-and-test-skill How do I package and test a custom skill in Claude before and after uploading? https://latestn.com/tool/claude-apps/features/pay-with-link How do I pay with Link in Claude Duet? https://latestn.com/tool/claude-apps/features/pay-with-shop-pay How do I pay with Shop Pay in Claude Duet? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T02:59:34Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-apps/features/plan-mode-and-clear-prompting/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-apps/features/plan-mode-and-clear-prompting POST: https://latestn.com/dispute/tool/claude-apps/features/plan-mode-and-clear-prompting with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-apps/features/plan-mode-and-clear-prompting?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I use Plan Mode and /clear to scope tasks in Claude Code? Revision 1, last verified 2026-11-20T12:06:44Z. https://latestn.com/tool/claude-apps/features/plan-mode-and-clear-prompting (accessed 2026-11-21T10:06:17Z). @misc{LatestN_tool_claude_apps_features_plan_mode_and_clear_prompting_r1, title = {How do I use Plan Mode and /clear to scope tasks in Claude Code?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-apps/features/plan-mode-and-clear-prompting}}, note = {Revision 1; digest sha256:85b24dd6f9366727; last verified 2026-11-20T12:06:44Z; accessed 2026-11-21T10:06:17Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-apps/features/plan-mode-and-clear-prompting