Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.1.186 adds CLI MCP auth, bash auto-response, SSH-friendly headless login, and richer workflow/plugin views.
$ git clone --branch v2.1.186 https://github.com/anthropics/claude-code.git # already have the repo? check out this version: $ git checkout v2.1.186
$ claude mcp login my-server --no-browser
# settings.json
{ "respondToBashCommands": false } - ›Adds
claude mcp login <name>andclaude mcp logout <name>to authenticate MCP servers directly from the CLI, with--no-browserstdin redirect for SSH sessions. - ›Adds
!bash command auto-response: Claude now automatically replies to bash command output; disable with"respondToBashCommands": falsein settings.json. - ›Adds status filtering (press
f) to the/workflowsagent detail view. - ›Adds a 'Skills' section to the
/pluginInstalled tab. - ›Adds
teammateMode: "iterm2"setting with a warning when auto mode cannot find theit2CLI.
+6 moreshow less
- ›Adds 'Claude Platform on AWS - refresh credentials' option to
/loginwhenawsAuthRefreshis configured. - ›Background subagents now surface permission prompts in the main session instead of auto-denying, showing which agent is asking; Esc denies just that tool.
- ›Improves memory: the agent is now reminded to compact its
MEMORY.mdindex when nearing the size limit. - ›Improves skill frontmatter to accept
display-name,default-enabled,fallback, andmetadata.*keys in kebab-case, snake_case, and camelCase. - ›Improves malformed
SKILL.mdYAML frontmatter handling: loads the skill body with empty metadata instead of failing silently. - ›Changes
/review <pr>to use the same review engine as/code-review medium.
- !
CLAUDE_CODE_MAX_RETRIESis now capped at 15; unattended sessions that relied on higher values must switch toCLAUDE_CODE_RETRY_WATCHDOGinstead.