/install-watchdog
Install the egregore watchdog daemon for automatic session relaunching
$ npx -y skills add athola/claude-night-market --agent claude-codeHow 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
/install-watchdog
Context preview
What this command does when you run it.
Install the egregore watchdog daemon for automatic session relaunching
Command definition
install-watchdog.mdname: install-watchdog description: >- Install the egregore watchdog daemon for automatic session relaunching usage: >- /egregore:install-watchdog [--window 5h|7d] [--interval SECONDS]
install-watchdog
Install a system-level daemon that monitors the egregore and relaunches it after crashes, rate limits, or context overflows.
What It Does
On macOS, installs a launchd agent (`com.egregore.watchdog`) that runs the watchdog script at a fixed interval. On Linux, installs a systemd user timer (`egregore-watchdog.timer`) instead.
The watchdog checks:
1. Whether active work items remain in the manifest. 2. Whether a cooldown period is still active. 3. Whether a session is already running (via pidfile).
If work remains and no session is running, the watchdog relaunches the egregore.
Prerequisites
- `jq` must be installed (used to parse manifest and
budget files).
- The `claude` CLI must be on your PATH.
Options
| Option | Default | Description | |--------------|---------|-------------------------------| | `--window` | `5h` | Time window for the session | | `--interval` | `300` | Check interval in seconds |
See Also
- `/egregore:uninstall-watchdog` to remove the daemon.
- `/egregore:summon` to start processing.
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Other commands on claude-night-market.
- /aggregate-logs
Generate LEARNINGS.md from skill execution logs.
Open command - /analyze-skill
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
Open command - /bulletproof-skill
Harden skills against rationalization and bypass behaviors
Open command - /context-report
Generate context optimization report for skill directories
Open command - /create-command
Create slash commands with brainstorming and best practices
Open command - /create-hook
Create hooks with brainstorming and security-first design
Open command

