Anthropic weighs killing Claude Code plan mode in favor of shift+tab effort levels
omarsar0 · x · 2026-09-24
- Anthropic is considering removing Claude Code's plan mode, replacing it with a shift+tab hotkey to adjust model effort levels.
- The rationale: current models no longer need explicit plan mode. The author still plans, but now via brainstorming in a doc with an artifact and checklists—planning happens more naturally with the models themselves.
- The team is soliciting feedback from plan mode diehards.
More from coding & agent
- Stripe launches claimable sandboxes: frictionless payment integrations for AI agents — jeff_weinstein · 2026-11-12
- Databricks launches autonomous AI coworker Genie: 91% on enterprise tasks with half the tokens — Yuchenj_UW · 2026-11-12
- Loom founder launches Roma 2.0, a shared to-do list that orchestrates AI agents — thetripathi58 · 2026-11-12
- Developer proposes a 'blast radius' test for AI agents before building — Few-Garlic2725 · 2026-11-12
- Sosumi Eval: Apple Docs Access Lifts Coding Agent Pass Rates from ~33% to 94-98% — JordanMorgan10 · 2026-11-12
- CypherGuard fixes structurally wrong LLM Cypher queries, hitting 88.5% on CypherBench — JeremyCMorgan · 2026-11-12