Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
v2.3.0: Remove blocking modal — compaction is now fully background with toast-only status. v2.2.0: Full background isolation — filter memory flush messages and COMPACTION divider from chat timeline. parentId skip-set constrained to message-only entries to prevent cascade.
What This Skill Does
Adds background memory compaction to the OpenClaw Control UI. Runs compaction without blocking the interface, triggers automatically when token usage exceeds a configurable threshold, and stores results with before/after token counts. Includes a settings tab with model selection and a context gauge button in the chat toolbar.
Runs entirely in the background via toasts instead of blocking the UI with a modal, so the chat remains interactive during compaction.
When to use it
- Compacting long agent sessions before context limit is hit
- Reviewing how much memory was freed after a compaction run
- Setting a custom model for compaction separate from the chat model
- Automatically compacting after every response once tokens cross 80%
- Reading the conversation summary paragraph in compacted output
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: compact this session automatically when it gets too full
- 1User opens the Compaction settings tab under the Agent nav group
- 2Enables auto-compaction toggle and sets threshold slider to 75%
- 3After the next chat response, token usage crosses 75% and auto-compaction triggers
- 4A toast appears showing "Auto-Compacting (77%)" while the UI stays interactive
- 5Compaction completes and the Last Compaction card shows tokens before, after, and percent reduction
Session memory compacted in the background; chat continues without interruption and result stored in compaction-config.json
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.