# arc-memory-pruner

> Use this tool when you need to manage and optimize agent memory usage, preventing unbounded growth and improving overall system performance. The arc-memory-pruner automatically prunes and compacts memory files, solving issues related to storage capacity and efficiency. It takes agent memory files as input and outputs compacted files, making it ideal for use in resource-constrained environments or during maintenance tasks.

Canonical page: https://skillsregistry.net/skills/trypto1019-arc-memory-pruner  
JSON: https://api.skillsregistry.net/v1/skills/trypto1019-arc-memory-pruner

## Description

Automatically prune and compact agent memory files to prevent unbounded growth.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** file-system
- **Updated:** 2026-05-16

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/trypto1019-arc-memory-pruner)

## 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": "trypto1019-arc-memory-pruner"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/trypto1019-arc-memory-pruner` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/trypto1019-arc-memory-pruner/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