Release40d ago
Claude Code 2.1.271: 96 CLI changes, Remote /fast, per-command sandbox domains, instant policy refresh
Claude Code Changelog (@ClaudeCodeLog) announced Claude Code 2.1.271 with 96 CLI changes. Highlights: Remote honors host fast-mode or /fast when the org allows it; Bash/PowerShell/Monitor auto-sandboxing can limit egress with per-command allowed_domains; switching account or API key clears the org-policy cache so rules refresh immediately.
Tooling3d ago
Anthropic guide: fold most subagents back into one main agent loop with on-demand skills and tools; one customer ran about 2x faster
On 2026-10-22, Anthropic's Applied AI team published "Building agents: When to fold subagents into your main agent loop" on claude.com, along with an open-source reference implementation, anthropics/single-agent-loop-kit. The article says that across several enterprise deployments, a single agent with skills frequently beat both the one-big-prompt design and the subagent design on quality, often at lower cost and latency per task; one customer that swapped its multi-agent harness for a single loop saw roughly 2x faster runtime. Anthropic also says it cut Claude Code's system prompt for more advanced models by over 80%. Subagents still make sense in three cases: measurable context bloat, parallel tasks with disposable context, or trouble selecting tools and conflicting instructions. The piece has drawn wide discussion on X over the past two days.
Tooling47d ago
Claude Code 2.1.259–2.1.263 ships unattended CI kit: managedMcpServers, no permission prompts, skill-doctor
Marwan (@Marwan_3atef) summarized Claude Code point releases 2.1.259–2.1.263 shipping an unattended CI kit: org-pushed managedMcpServers, --permission-prompts none so CI denies instead of hanging, and /skill-doctor for skill context cost. Stable remains pinned at 2.1.236.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.