# janitor

> Use this tool when you need to efficiently manage and clean up AI sessions, as it solves problems related to resource optimization and data consistency by automating the removal of unnecessary data and sessions, accepting input parameters for customization and outputting a cleaned and organized environment for improved performance. It is particularly useful in contexts where multiple AI sessions are run concurrently or where data accumulation affects system efficiency.

Canonical page: https://skillsregistry.net/skills/sarthib7-janitor  
JSON: https://api.skillsregistry.net/v1/skills/sarthib7-janitor

## Description

**Janitor** is an intelligent cleanup and session management skill for OpenClaw AI agents.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-23

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-08-23

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/sarthib7-janitor)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sarthib7-janitor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sarthib7-janitor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sarthib7-janitor/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt