The Clauders Journal
Signals from the Claude Code community.
Weekly field notes on releases, security boundaries, agent patterns, open-source projects, and the people building with Claude Code.
Start here
Latest dispatch
What's Up Claude Code: Week of August 3rd
Anthropic made auto mode the coming default, shipped self-hosted Claude Code runners and cross-session messaging, and pushed six releases through a week dominated by security boundaries and longer-running agents.
Keep reading
Recent dispatches
What's Up Claude Code: Week of July 27th
Claude Code v2.1.220 spent the week accumulating reliability and guardrail reports, Anthropic published the working kit behind its large-scale migration playbook, and a new model price war made harness efficiency impossible to ignore.
What's Up Claude Code: Week of July 20th
Claude Opus 5 became the everyday frontier model, Claude Code v2.1.219 reopened nested subagents with stricter sandbox controls, and Anthropic's new context-engineering guidance told teams to delete most of their accumulated prompt rules.
What's Up Claude Code: Week of July 13th
Claude Code v2.1.214 shipped a major permission-hardening release, Anthropic clarified Fable 5 access and extended weekly limits, and a week of worktree, hook, and subagent failures made the case for enforceable agent boundaries.
What's Up Claude Code: Week of July 6th
Claude Code v2.1.207 fixed streaming lag and hardened plugins, Fable 5 access was extended while safeguard fallbacks spread, and the real cost story moved from tokens to cache-aware orchestration.
Earlier signals