Setup & Installation
openclaw skills install @trypto1019/arc-memory-pruner
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install arc-memory-pruner
Version History
v1.1.0Feb 17, 2026 - Version note by skill developer:
- Version bump to 1.1.0. - scripts/memory_pruner.py updated.
What This Skill Does
Prunes and compacts agent memory files to prevent unbounded growth. Enforces line limits, rotates log directories with a circular buffer, and removes stale state entries by date. Includes a dry-run mode to preview changes before applying them.
Combines log rotation, date-based compaction, and line-based pruning in a single script rather than requiring separate tools for each operation.
When to use it
- Trimming agent wake-state files that have grown too large
- Rotating log directories to keep only the last 7 runs
- Removing outdated state entries older than a specific date
- Checking memory file sizes before a long agent session
- Previewing what would be deleted before committing a prune
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: prune my wake-state.md to the last 200 lines
AGENT
- 1Runs dry-run to preview which lines would be removed
- 2Checks current file size with the stats command
- 3Executes prune with --max-lines 200 to trim the file
- 4Confirms updated line count and new file size
OUTPUT
wake-state.md trimmed to 200 lines with older entries removed