Claude Code v2.1.261 ships skill-doctor, 128K output caps and input fixes
ashwin-ant · ghdev · 2026-09-05
Highlights
anthropics/claude-code released v2.1.261:
- New /skill-doctor command shows which loaded skills go unused and what they cost in context, so you can prune them
- New bashOutputMaxChars and taskOutputMaxChars settings raise inline command/background-task output limits up to 128K characters before spilling to files
- --append-subagent-system-prompt-file lets you load oversized subagent system prompts from a file
- /status and claude doctor now include an "Organization policy" line explaining why policy loading failed (e.g. a proxy not passing the endpoint)
- Numerous fixes: dropped/out-of-order keystrokes, lost hook output and parallel-tool-call context on session resume, Bedrock wizard hangs behind unresponsive proxies, stale Remote Control permission modes, and more
More from coding & agent
- PostgreSQL 19 slips to November as LLM-assisted code review floods committers with edge cases — sanjaykalra · 2026-10-21
- LangChain adds Human-in-the-Loop beta to Managed Deep Agents — LangChain · 2026-10-21
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21
- Open-sourced pixel art normals generator ships as Rust CLI and wasm library — HugoDuprez · 2026-10-20
- Eval researcher teases guide to subjective-task evals, with a curated resource list — cwolferesearch · 2026-10-20
- Eon cuts engineer onboarding from 2 days to 2 minutes with an MCP Gateway on Bedrock AgentCore — AWS ML Blog · 2026-10-20