swarm-janitorEnterprise-grade OpenClaw skill for cleaning up orphaned subagent processes, archiving transcripts to SuperMemory, and freeing disk space without losing work. Features dry-run mode, configurable retention policies, and comprehensive safety checks.
Install via ClawdBot CLI:
clawdbot install lvcidpsyche/swarm-janitorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses system directories or attempts privilege escalation
/var/log/Calls external URL not in known-safe list
https://github.com/openclawdad/swarm-janitorAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
A team managing multiple AI subagents for software development and testing, where orphaned processes accumulate over time. This skill automates cleanup to free disk space and archive transcripts for compliance, ensuring system performance without manual intervention.
Researchers running numerous AI subagents for data analysis and simulations, leading to session clutter and resource waste. The skill safely archives results to SuperMemory before cleanup, preserving valuable data while optimizing storage usage.
A company using AI subagents for handling customer inquiries, where sessions can become orphaned due to errors or restarts. This tool maintains system efficiency by cleaning up old sessions and backing up transcripts for audit trails and quality assurance.
Financial firms deploying AI subagents for real-time market analysis and risk assessment, requiring strict data retention and system hygiene. The skill ensures orphaned processes are removed after archival, supporting regulatory compliance and operational stability.
Offer the skill as free open-source software, with paid support, customization, and premium features like advanced analytics or integration services for large organizations. Revenue comes from subscription-based support contracts and consulting fees.
Provide a cloud-based service that integrates this skill with other AI tools, offering automated cleanup, monitoring dashboards, and compliance reporting. Revenue is generated through monthly or annual SaaS subscriptions based on usage tiers and features.
License the skill to AI platform providers as an embedded module for maintenance and memory management. Revenue comes from one-time licensing fees or royalties per deployment, targeting companies building comprehensive AI ecosystems.
💬 Integration Tip
Ensure SuperMemory is properly configured with API keys before enabling archival, and test with dry-run mode first to preview cleanup actions without risk.
Scored May 17, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...