Context Budgeting

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.

Before installing, understand that the skill may change local OpenClaw memory/checkpoint state and run its bundled compaction script. Review the script if you are cautious about local automation, but the supplied evidence does not show unrelated access, credential handling, exfiltration, or destructive behavior.

Type: OpenClaw Skill Name: context-budgeting Version: 1.0.0 The skill bundle is classified as benign. The `SKILL.md` instructs the OpenClaw agent to manage its context window by updating a specific memory file (`memory/hot/HOT_MEMORY.md`) and executing a local shell script (`scripts/gc_and_checkpoint.sh`). The script's primary action is to call the internal `openclaw sessions --active 1` command, which is directly aligned with the stated purpose of session compaction and context budgeting. There is no evidence of data exfiltration, malicious execution (e.g., remote payload fetching), persistence mechanisms, or prompt injection attempts to subvert the agent's core directives or access unrelated sensitive data. The commented-out `find` command for large temporary files is a diagnostic/cleanup step, not a security risk.