--dangerously-skip-permissions
A Claude Code CLI flag, read out of the shipped bundle. It has been in the build since v2.1.138, including the newest one read.
Skip permission prompts. Equivalent to --permission-mode bypassPermissions. See permission modes for what this does and does not skip. For sessions started with --bg, the mode persists when the supervisor restarts the session
Anthropic's own wording. Read off CLI reference, captured 2026-09-26.
In the changelogs
14Releases whose published page names --dangerously-skip-permissions.
-
v2.1.292
Teammate permission flags now consider whether auto mode was picked by level
When starting a teammate, Claude Code now factors in whether auto mode was chosen by level; the flags sent for each mode are unchanged
found in this entry's text
-
v2.1.290
New --proactivity flag sets how much Claude does on its own at startup
A
--proactivityflag picks the proactivity level when Claude Code starts, andCLAUDE_CODE_DISABLE_PROACTIVITYturns the selector offfound in this entry's text
-
v2.1.290
New variables to turn off proactivity and carry it across a relaunch
Claude Code adds
CLAUDE_CODE_DISABLE_PROACTIVITYand variables that pass proactivity state to a relaunched Claude Codefound in this entry's text
-
v2.1.290
A proactivity level can set the permission mode a session starts in
When a proactivity level other than default is set, Claude Code can choose the starting permission mode from it
found in this entry's text
-
v2.1.281
Hidden
claude -p --cloudheadless cloud-print path added, but compiled offCode for a headless
claude -p --cloudrun is added, but the switch that enables it returns false, so no one can use it in 2.1.281found in this entry's text
-
v2.1.274
Structured exit-reason telemetry added to early CLI startup failures
Early CLI startup failures now report a categorized reason via telemetry before exiting
found in this entry's text
-
v2.1.269
New CLI flags for the plugin-eval command: --trust-plugin and --allow-real-servers
claude plugin evaladds--trust-pluginfor CI and--allow-real-serversto run real MCP servers without mocksfound in this entry's text
-
v2.1.242
Cloud-hosted sessions now refuse local CLI options instead of quietly dropping them
Running with --cloud now tells you which local CLI options were ignored or refused, and why.
found in this entry's text
-
v2.1.224
Control-tag sanitizing rules are now shared
The rules that neutralise control tags in subagent output are now shared with a new assistant-output scanner.
found in this entry's text
-
v2.1.202
bypassPermissionsMode Not Restored from Sessions Unless Explicitly Launchedfound in this entry's text
-
v2.1.122
Background Job Safety Guards
found in this entry's text
-
v2.0.37
Permission Bypass Notifications
found in this entry's text
-
v2.0.29
Enhanced Trust Validation Logic
found in this entry's text
- v0.2.44
First cited
1The earliest release whose published evidence quoted --dangerously-skip-permissions was v2.1.281, 23 Sep 2026. That is the oldest release this project wrote about it, so it is a floor on the name's age and not the release that introduced it. It is not a presence reading: which builds carried the name is the table below.
Presence across releases
1Build by build
149One row per release since the first build this name was read out of. Absent means the build was read and the name was not in it, never mined means no bundle for that release was ever archived, and a declared type or a default is only ever what that release's own bundle stated.
Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the CLI flag does. All CLI flags.