/dismiss
The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state.
$ 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
/dismiss
Context preview
What this command does when you run it.
The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state.
Command definition
dismiss.mdname: dismiss
description: >-
The ONLY way to stop the egregore. Human-initiated
graceful shutdown that saves all state.
usage: /egregore:dismiss
dismiss
The sole mechanism for stopping the egregore. The egregore runs indefinitely by default and will never stop on its own. Only a human issuing this command can end an egregore session.
All in-progress work is saved so it can be resumed later with `/egregore:summon`.
What It Does
1. Marks all active work items as `paused` in `.egregore/manifest.json`. 2. Saves the current pipeline position for each item so resumption starts at the right step. 3. Cancels any scheduled cron jobs (progress pulses, work-scan polls) created by the orchestrator. 4. Removes the pidfile (`.egregore/pid`) so the watchdog does not relaunch the session. 5. Logs the dismissal event to the decision log.
Important
The egregore never dismisses itself. It is designed to run autonomously and indefinitely, scanning for new work after completing its current manifest. This command is the only way to interrupt that cycle.
If you want the egregore to stop after processing a fixed set of items without manual intervention, use `/egregore:summon --bounded` instead of dismissing.
When To Use
- You need to reclaim your machine or API quota.
- You want to review progress before the egregore
continues.
- Something went wrong and you want to stop processing
before more items are affected.
- You are done with the egregore for now and want a
clean shutdown.
See Also
- `/egregore:summon` to start or resume processing.
- `/egregore:status` to review current state before
dismissing.
Read more
name: dismiss description: >- The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state. usage: /egregore:dismiss
dismiss
The sole mechanism for stopping the egregore. The egregore runs indefinitely by default and will never stop on its own. Only a human issuing this command can end an egregore session.
All in-progress work is saved so it can be resumed later with `/egregore:summon`.
What It Does
1. Marks all active work items as `paused` in `.egregore/manifest.json`. 2. Saves the current pipeline position for each item so resumption starts at the right step. 3. Cancels any scheduled cron jobs (progress pulses, work-scan polls) created by the orchestrator. 4. Removes the pidfile (`.egregore/pid`) so the watchdog does not relaunch the session. 5. Logs the dismissal event to the decision log.
Important
The egregore never dismisses itself. It is designed to run autonomously and indefinitely, scanning for new work after completing its current manifest. This command is the only way to interrupt that cycle.
If you want the egregore to stop after processing a fixed set of items without manual intervention, use `/egregore:summon --bounded` instead of dismissing.
When To Use
- You need to reclaim your machine or API quota.
- You want to review progress before the egregore
continues.
- Something went wrong and you want to stop processing
before more items are affected.
- You are done with the egregore for now and want a
clean shutdown.
See Also
- `/egregore:summon` to start or resume processing.
- `/egregore:status` to review current state before
dismissing.
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

