# Claude Code 2.1.261 By Steven Van · 2026-09-04 The update adds output-size and skill-usage settings, plus fixes for input dropouts, Bedrock setup and plugin syncing. Version 2.1.261 of [Claude Code]() adds a few settings for tuning how much output and context the agent handles, plus a batch of fixes. - **/status** and claude doctor now show an "Organization policy" line explaining why an organization's policy failed to load, for example when a proxy isn't passing the endpoint through. - New **bashOutputMaxChars** and **taskOutputMaxChars** settings raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters. - **--append-subagent-system-prompt-file** reads the subagent system prompt from a file, for prompts too large to pass on the command line. - **/skill-doctor** shows which loaded skills go unused and what they cost in context, so they can be pruned. ## Fixes - Typed or pasted characters occasionally landing out of order or being dropped during fast input or key repeat. - **/add-dir** printing a false "couldn't be resolved" error when the working directory is on a /net automount. - The Bedrock setup wizard hanging when AWS or an AWS credential helper never responds, it now times out with a clear error, and its model checks failing behind a TLS-inspecting proxy. - Cloud sessions discarding a plugin synced from claude.ai when managed settings force-enable it in enabledPlugins. Full details are in the [changelog](). [![]()]() ![Claude Code]() Claude Code Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud. [View Claude Code →]() [Original source]() [Read Claude Code 2.1.261 on Creators Toolbox]() --- Canonical source: https://creatorstoolbox.com/blog/claude-code-claude-code-2-1-261