{"version":"2.1.169","anchor":"safe-mode-safe-mode-claude-code-safe-mode","canonical_anchor":"safe-mode-safe-mode-claude-code-safe-mode","heading":"Safe Mode ( --safe-mode \/ CLAUDE_CODE_SAFE_MODE )","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.169\/e\/safe-mode-safe-mode-claude-code-safe-mode","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.169","markdown":"### Safe Mode (`--safe-mode` \/ `CLAUDE_CODE_SAFE_MODE`)\n\n**What**\n\nA new opt-in mode that disables all per-user and per-project customizations for a session. Designed for troubleshooting when Claude Code behaves unexpectedly and you want to isolate whether a plugin, hook, or CLAUDE.md is the cause.\n\n**Usage**\n\n`claude --safe-mode # or CLAUDE_CODE_SAFE_MODE=1 claude` **Details** - Disables: CLAUDE.md, skills, plugins, plugin hooks, MCP servers (auto-discovered and claude.ai), custom agents, output styles, workflows, custom themes, and custom keybindings - Managed policy settings and hooks (from your organization's policy) still apply - The UI surfaces a warning banner so you know safe mode is active - Settings dialogs show \"disabled in safe mode\" labels next to affected options - To exit safe mode: remove the flag or unset the env var and restart (`claude` will tell you which applies) - The `--agents` flag is silently ignored in safe mode (user-supplied agents are disabled) **Evidence** Safe mode toggle (search for `\"CLAUDE_CODE_SAFE_MODE\"` and `\"--safe-mode\"`) \u2014 `C9()` function at line ~3884"}