Menü
Clean up old workflow state directories to free disk space
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Generate a PRD for a feature using Memory Bank context
Generate a technical specification based on a PRD using Memory Bank context
Run Memory Bank doc gardening (maintenance / garbage collection)
"Process and implement tasks from a protocol in git worktrees (or inline on the main workdir)"
Update Memory Bank documentation after code changes or protocol completion
Defer an out-of-scope finding to the backlog. Use when a bug, tech debt, idea, or risk is discovered but not appropriate to solve now.
| name | cleanup |
| description | Clean up old workflow state directories to free disk space |
| version | 1.0.0 |
Remove old .workflow-state/ run directories to free disk space.
Call mcp__plugin_memento-workflow_memento-workflow__cleanup_runs with:
cwd: project directory (defaults to .)before: remove runs started before this date (ISO 8601 or YYYY-MM-DD)status_filter: only remove runs with this status (completed, running, error)keep: keep the N most recent matching runs (default: 0)dry_run: preview what would be deleted without deletingremove_all: remove ALL runs (ignores other filters)| Goal | Parameters |
|---|---|
| Remove all completed runs older than a week | before: "2026-03-07", status_filter: "completed" |
| Remove everything, keep last 5 | remove_all: true, keep: 5 |
| Preview cleanup | remove_all: true, dry_run: true |
| Remove orphaned/stuck runs | status_filter: "running" |
cd memento-workflow
python -m scripts.cleanup --before 2026-03-01
python -m scripts.cleanup --status completed --keep 5
python -m scripts.cleanup --all --dry-run