Claude Code Drops Ultraplan: Why Are Cloud Agent Workflows Hard to Land?
HankYeomans · x · 2026-08-07
Anthropic recently and quietly removed the Ultraplan feature from the latest version of Claude Code. The feature previously launched an entire agent workflow in Plan Mode to produce a complete implementation spec from a single request.
Commentators suggest this isn't because the idea failed, but because the execution environment is incredibly challenging. Implementing cloud-based agent workflows is tough: every sandbox must be meticulously configured with integrations, scripts, environment variables, secrets, network access, and permissions. For a planning workflow, repository access alone is a small part of the picture; agents also need to understand the broader engineering environment, including related repositories, production infrastructure, deployment targets, internal services, and documentation. Existing local machine environments naturally provide much of this context for agents.
More from coding & agent
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- Comparing AI Subscriptions: DeepSeek API vs. Claude Pro vs. Local LLMs — Unlikely_Bluejay5392 · 2026-08-24
- Claude Code introduces 'Remote Control' feature to boost coding efficiency — rohanpaul_ai · 2026-08-24
- rauchg lays out fx extension philosophy: MCP, Skills, Plugins and Unix composition — AccBalanced · 2026-08-24
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- smolvm passes Simon Willison's Fable 5 agent test as a secure sandbox — yawnxyz · 2026-08-24