Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks.
- Initial release of the context-budgeting skill for OpenClaw agents. - Provides a structured method to partition the agent's context window by priority: goals, recent history, decision logs, and relevant knowledge. - Introduces mandatory pre-compression checkpointing to preserve key task data before context compaction. - Adds an automation script (`gc_and_checkpoint.sh`) for efficient memory cleanup without session restart. - Integrates with the agent's heartbeat to automatically trigger context management when usage exceeds 80%.