/hs
Hardstop - Pre-execution safety layer for shell commands. Shows status and help.
$ npx -y skills add frmoretto/hardstop --agent claude-codeShips with hs. Installing the plugin gets this command.
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/hs
Context preview
What this command does when you run it.
Hardstop - Pre-execution safety layer for shell commands. Shows status and help.
Command definition
hs.mddescription: Hardstop - Pre-execution safety layer for shell commands. Shows status and help.
argument-hint: [on|off|skip|status|log|help]
allowed-tools: ["Bash"]
Hardstop Command
Hardstop is a pre-execution safety layer that blocks dangerous shell commands using pattern matching + LLM analysis.
Context
- State directory: `~/.hardstop/`
- State file: `~/.hardstop/state.json`
- Skip flag: `~/.hardstop/skip_next`
- Audit log: `~/.hardstop/audit.log`
Your Task
Based on the argument provided (`$ARGUMENTS`), perform the appropriate action:
If no argument or "help" or "status":
Run this command to show current status:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" statusIf argument is "on" or "enable":
Use `/on` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" onIf argument is "off" or "disable":
Use `/off` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" offIf argument is "skip" or "bypass":
Use `/skip` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" $ARGUMENTSIf argument is "log" or "logs" or "audit":
Use `/log` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" logAvailable Commands
- `/hs` or `/hs status` - Show current status
- `/hs on` - Enable protection
- `/hs off` - Disable protection temporarily
- `/hs skip` - Skip safety check for next command only
- `/hs log` - Show recent audit log entries
- `/hs help` - Show this help
Or use the shorthand commands directly:
- `/on` - Enable protection
- `/off` - Disable protection
- `/skip` - Skip next command
- `/status` - Show status
- `/log` - Show audit log
Read more
description: Hardstop - Pre-execution safety layer for shell commands. Shows status and help. argument-hint: [on|off|skip|status|log|help] allowed-tools: ["Bash"]
Hardstop Command
Hardstop is a pre-execution safety layer that blocks dangerous shell commands using pattern matching + LLM analysis.
Context
- State directory: `~/.hardstop/`
- State file: `~/.hardstop/state.json`
- Skip flag: `~/.hardstop/skip_next`
- Audit log: `~/.hardstop/audit.log`
Your Task
Based on the argument provided (`$ARGUMENTS`), perform the appropriate action:
If no argument or "help" or "status":
Run this command to show current status:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" statusIf argument is "on" or "enable":
Use `/on` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" onIf argument is "off" or "disable":
Use `/off` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" offIf argument is "skip" or "bypass":
Use `/skip` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" $ARGUMENTSIf argument is "log" or "logs" or "audit":
Use `/log` command instead, or run:
python "${CLAUDE_PLUGIN_ROOT}/commands/hs_cmd.py" logAvailable Commands
- `/hs` or `/hs status` - Show current status
- `/hs on` - Enable protection
- `/hs off` - Disable protection temporarily
- `/hs skip` - Skip safety check for next command only
- `/hs log` - Show recent audit log entries
- `/hs help` - Show this help
Or use the shorthand commands directly:
- `/on` - Enable protection
- `/off` - Disable protection
- `/skip` - Skip next command
- `/status` - Show status
- `/log` - Show audit log
👉 ⭐ Star on GitHub if Hardstop keeps you safe! Pre-execution safety validation for AI coding agents.
Repo: frmoretto/hardstop