Setup & Installation
openclaw skills install @sarielwang93/context-budgeting
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install context-budgeting
What This Skill Does
A framework for managing context window usage in OpenClaw agents. It partitions context into defined zones (goals, history, decisions, background knowledge), checkpoints state before compaction, and runs a cleanup script to recover capacity without restarting the session.
Checkpointing to HOT_MEMORY.md before compaction preserves task state that standard compaction would otherwise discard, allowing the agent to resume accurately.
When to use it
- Preventing memory loss during long multi-step coding sessions
- Recovering task state after automatic context compaction
- Reducing token costs on extended agent workflows
- Managing multi-megabyte JSON outputs without flooding the context
- Keeping long-running agents on track past the 80% context threshold
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Keep my refactoring task going after the context fills up
AGENT
- 1Check current context usage via /status
- 2Confirm context exceeds 80% threshold
- 3Update memory/hot/HOT_MEMORY.md with current status, key decisions made, and next step
- 4Execute scripts/gc_and_checkpoint.sh to clear raw data and finalize compaction
- 5Resume the task using the checkpoint as the new working context
OUTPUT
Task continues from the last checkpoint without losing prior decisions or progress