/summon
Summon the egregore to autonomously process work items through the full development lifecycle. Runs indefinitely by default until dismissed.
$ 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
/summon
Context preview
What this command does when you run it.
Summon the egregore to autonomously process work items through the full development lifecycle. Runs indefinitely by default until dismissed.
Command definition
summon.mdname: summon
description: >-
Summon the egregore to autonomously process work items
through the full development lifecycle. Runs indefinitely
by default until dismissed.
usage: >-
/egregore:summon "<prompt>" [--window 5h|7d]
[--bounded] [--issues N,N] [--issues-label LABEL]
summon
Launch the egregore to autonomously process work items through planning, implementation, testing, and PR creation. By default the egregore runs indefinitely, scanning for new work after completing its current manifest. Use `/egregore:dismiss` to stop it.
When To Use
- You have one or more issues or tasks to process
without manual intervention.
- You want to run a multi-hour or multi-day development
pipeline overnight or over a weekend.
- You want the agent to self-recover from crashes and
rate limits via the watchdog.
- You want continuous autonomous processing that finds
and handles new work as it appears.
When NOT To Use
- For quick, single-file changes. Just do them directly.
- When you need tight human-in-the-loop review at every
step. Use normal Claude sessions instead.
- On repositories you do not trust the agent to modify.
Egregore creates branches and opens PRs autonomously.
Usage
From a prompt:
/egregore:summon "Refactor the auth module to use JWT"
From GitHub issues by number:
/egregore:summon --issues 42,43,44
From GitHub issues by label:
/egregore:summon --issues-label "egregore"
Bounded mode (stops when time window expires):
/egregore:summon --bounded --window 2d --issues 42,43,44
Options
| Option | Default | Description | |------------------|---------|------------------------------| | `<prompt>` | none | Free-text work description | | `--window` | `5h` | Time window (e.g. 5h, 7d) | | `--bounded` | false | Stop when time window expires| | `--issues` | none | Comma-separated issue numbers| | `--issues-label` | none | GitHub label to pull issues |
The egregore runs indefinitely by default. Pass `--bounded` to set a hard time limit. In both modes, the egregore scans for new work after completing all current items. The only difference is that bounded mode exits when the time window expires.
What Happens
1. Egregore parses the prompt or fetches issues. 2. Work items are written to `.egregore/manifest.json`. 3. Each item moves through the pipeline: plan, implement, test, PR. 4. On crash or rate limit, the watchdog relaunches the session automatically. 5. When all current items are completed or failed, the egregore scans for new work:
- Fetches open GitHub issues with the configured label.
- Scans for untracked `TODO`/`FIXME` comments.
- Runs the test suite and checks for new failures.
- Checks for open PRs needing review fixes.
6. New work items are added to the manifest and the cycle repeats from step 3. 7. This loop continues indefinitely until you run `/egregore:dismiss` to stop it.
In `--bounded` mode, steps 5-7 still happen but the egregore exits when the time window expires. It does NOT stop just because the initial items are done.
Stopping the Egregore
The egregore does not stop on its own. To shut it down:
/egregore:dismiss
This pauses all active work items, saves state, and removes the pidfile. You can resume later with another `/egregore:summon`.
Progress Monitoring (2.1.71+)
While the egregore runs, you can monitor progress with `/loop`:
/loop 5m /egregore:status
This emits a status summary every 5 minutes between turns. The egregore also schedules this automatically on startup.
See Also
- `/egregore:status` to check progress.
- `/egregore:dismiss` to stop gracefully.
- `/egregore:install-watchdog` to enable auto-relaunch.
Read more
name: summon description: >- Summon the egregore to autonomously process work items through the full development lifecycle. Runs indefinitely by default until dismissed. usage: >- /egregore:summon "<prompt>" [--window 5h|7d] [--bounded] [--issues N,N] [--issues-label LABEL]
summon
Launch the egregore to autonomously process work items through planning, implementation, testing, and PR creation. By default the egregore runs indefinitely, scanning for new work after completing its current manifest. Use `/egregore:dismiss` to stop it.
When To Use
- You have one or more issues or tasks to process
without manual intervention.
- You want to run a multi-hour or multi-day development
pipeline overnight or over a weekend.
- You want the agent to self-recover from crashes and
rate limits via the watchdog.
- You want continuous autonomous processing that finds
and handles new work as it appears.
When NOT To Use
- For quick, single-file changes. Just do them directly.
- When you need tight human-in-the-loop review at every
step. Use normal Claude sessions instead.
- On repositories you do not trust the agent to modify.
Egregore creates branches and opens PRs autonomously.
Usage
From a prompt:
/egregore:summon "Refactor the auth module to use JWT"
From GitHub issues by number:
/egregore:summon --issues 42,43,44
From GitHub issues by label:
/egregore:summon --issues-label "egregore"
Bounded mode (stops when time window expires):
/egregore:summon --bounded --window 2d --issues 42,43,44
Options
| Option | Default | Description | |------------------|---------|------------------------------| | `<prompt>` | none | Free-text work description | | `--window` | `5h` | Time window (e.g. 5h, 7d) | | `--bounded` | false | Stop when time window expires| | `--issues` | none | Comma-separated issue numbers| | `--issues-label` | none | GitHub label to pull issues |
The egregore runs indefinitely by default. Pass `--bounded` to set a hard time limit. In both modes, the egregore scans for new work after completing all current items. The only difference is that bounded mode exits when the time window expires.
What Happens
1. Egregore parses the prompt or fetches issues. 2. Work items are written to `.egregore/manifest.json`. 3. Each item moves through the pipeline: plan, implement, test, PR. 4. On crash or rate limit, the watchdog relaunches the session automatically. 5. When all current items are completed or failed, the egregore scans for new work:
- Fetches open GitHub issues with the configured label.
- Scans for untracked `TODO`/`FIXME` comments.
- Runs the test suite and checks for new failures.
- Checks for open PRs needing review fixes.
6. New work items are added to the manifest and the cycle repeats from step 3. 7. This loop continues indefinitely until you run `/egregore:dismiss` to stop it.
In `--bounded` mode, steps 5-7 still happen but the egregore exits when the time window expires. It does NOT stop just because the initial items are done.
Stopping the Egregore
The egregore does not stop on its own. To shut it down:
/egregore:dismiss
This pauses all active work items, saves state, and removes the pidfile. You can resume later with another `/egregore:summon`.
Progress Monitoring (2.1.71+)
While the egregore runs, you can monitor progress with `/loop`:
/loop 5m /egregore:status
This emits a status summary every 5 minutes between turns. The egregore also schedules this automatically on startup.
See Also
- `/egregore:status` to check progress.
- `/egregore:dismiss` to stop gracefully.
- `/egregore:install-watchdog` to enable auto-relaunch.
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

