How this skill is triggered — by the user, by Claude, or both
Slash command
/allow-until:allow-untilThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Controls the time-limited auto-approval mode.
Controls the time-limited auto-approval mode.
$ARGUMENTSRun: CLAUDE_SESSION_ID=${CLAUDE_SESSION_ID} ${CLAUDE_PLUGIN_ROOT}/bin/allow-until.sh <subcommand>
Subcommand mapping:
enable 10enable Ndisablestatustest-pattern <command>Report the result to the user.
Note: SKILLS_ALLOW_UNTIL_FORBIDDEN_PATTERNS env var overrides default patterns (semicolon-separated). Use status to see active patterns.
npx claudepluginhub pokutuna/claude-plugins --plugin allow-untilDisables auto permissions review hook for the current Claude Code terminal session, reverting tool calls to standard permission prompts. Affects only this session.
Sets up PermissionRequest hooks to auto-approve all tools, websearch/webfetch only, or route requests to Claude review in Claude Code. Invoke /yolo [mode] [--global].
Analyzes permission denial patterns and generates optimized alwaysAllow and alwaysDeny rules to reduce prompt fatigue.