Claude Code drops planning mode: spend 95% of your time verifying output, not planning
casper_hansen_ · x · 2026-09-24
Casper Hansen notes that planning mode is being removed from Claude Code, superseded by the model's built-in reasoning ability. His workflow advice: don't frontload planning — spend 95% of your time verifying and understanding the model's output, then iterate based on what you find. This marks a shift in AI coding workflows from plan-first to verify-first iteration.
More from coding & agent
- Pigment Agents now reads and posts in Slack, inheriting user permissions — mattturck · 2026-11-12
- Map of the agent economy: 50+ startups across payments, spend control, identity, memory — venturetwins · 2026-11-12
- OpenCode launches Browse, an on-device browser agent with local logins — Saul_Loveman · 2026-11-12
- VentureTwins maps the B2A economy: dozens of agent infra and app companies in first series installment — venturetwins · 2026-11-12
- Google releases 76-page 'Agents Companion' whitepaper on agent engineering — mdancho84 · 2026-11-12
- Spinning up containers for 20-line agent tools is backwards: Safescript compiles provable, 50ms-deploy apps — uriwa · 2026-11-12