From learnship
Activates safety mode: warns on destructive commands, locks file scope to path or disables with 'off'. Argument: [scope|off]
How this command is triggered — by the user, by Claude, or both
Slash command
/learnship:guard [scope|off]learnship/This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
<execution_context> @~/.claude/workflows/guard.md </execution_context> <context> Arguments: $ARGUMENTS </context> <process> Execute the learnship guard workflow end-to-end. Preserve all workflow gates, validations, checkpoints, and routing. </process>
<execution_context> @~/.claude/workflows/guard.md </execution_context>
Arguments: $ARGUMENTS Execute the learnship guard workflow end-to-end. Preserve all workflow gates, validations, checkpoints, and routing.npx claudepluginhub faviovazquez/learnship-marketplace --plugin learnship/guardActivates safety guardrails that block destructive Bash commands (rm -rf), SQL drops (DROP TABLE), git force-pushes, and optionally restrict file edits to a directory. Explains each block.
/guardActivates careful mode (destructive operation warnings) and freeze mode (directory lock) simultaneously for maximum safety, restricting edits to the specified directory.
/safe-modeActivates protective modes against destructive operations: cautious warns on risky Bash/git commands; lockdown restricts edits to a path; clear disables all. Reports status.
/guardActivates guard mode: enables warnings for destructive commands (rm -rf, git push --force) and restricts edits to the specified directory. Without arg, activates only warnings.
/setupInstalls project-specific workflow guards and CI pipelines — pre-commit hooks, CI workflows, AI bodyguard, and destructive-command guard. Also supports one-pass setup via --all.
/thumbgate-guardConverts the last agent mistake into a hard prevention rule that blocks the same tool call in future sessions. Wraps ThumbGate's capture and force-promote path.