Claude Code v2.1.300 adds /advisor, cache token metrics, mod hooks
ashwin-ant · ghdev · 2026-10-15
anthropics/claude-code released v2.1.300 with notable additions: virtualText prompt decorations for mods; OpenTelemetry cachecreation5m/1h token metrics; $.ui.view({agentId}) to inspect agent transcripts; a /advisor command on Claude Platform on AWS; support for rewriting workflow agents' prompt and model in agent.spawn hooks; a new prompt.change mod hook; plus fixes for cloud-session policy misreporting, /autocompact warnings, and SessionEnd hook reliability.
More from coding & agent
- ChipAgents and NVIDIA launch Build-A-Chip-Bench: top AI model scores just 16.6% on end-to-end chip design — WilliamWangNLP · 2026-10-15
- Alexandria Launches Product Search for Agents: 50+ Providers, 1 API Key — devdigest · 2026-10-15
- One user's AI stack: a Grok Bot agent team for daily life plus Claude Code as the workhorse — dscape · 2026-10-15
- Tencent and Fudan's WorkForge synthesizes 16.7K verifiable environments, lifting GDPVal from 45.5 to 73.6 — Tencent-Hunyuan · 2026-10-15
- LangChain Details 5 Context Engineering Techniques in Deep Agents to Fight Context Rot — LangChain · 2026-10-15
- Claude Code desktop app overhaul makes running parallel sessions much easier — ns123abc · 2026-10-15