Is plan mode on the chopping block? Users push back on Claude Code proposal
josephdviviano · x · 2026-09-24
An Anthropic team member floated removing plan mode in favor of a shift+tab hotkey for adjusting effort levels, arguing models no longer need it, and asked plan-mode diehards for feedback.
User josephdviviano pushed back: plan mode remains the cheapest way to confirm the agent actually understands the task, avoiding baking in 20 incorrect assumptions. The exchange highlights a core tension in coding agent design: keep explicit plan confirmation as models improve, or shift control granularity to effort dials.
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