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
- Reef launches inference-native infra that serves self-improving agents without downtime — pliang279 · 2026-09-05
- OpenAI Employee Uses GPT-6 Astra in Codex to Edit Official ChatGPT Instagram Videos — craigsdennis · 2026-09-05
- Gemini 3.8 Flash beats larger models on agent benchmarks, built for cheap scale — VraserX · 2026-09-05
- GPT-6 Astra rolls out to all Pro and Business users, with prompt and skills tuning tips — reach_vb · 2026-09-05
- Dev rebuilds $13M/yr app without Xcode, ships full mobile stack in a day — PrajwalTomar_ · 2026-09-05
- Google Cloud proposes Cloud Run sandboxes to fix coding agents' repair loop — rseroter · 2026-09-05