Session Watchdog

Monitors session context usage and saves checkpoints when approaching limits to prevent data loss before compaction or long tasks.

This skill appears to do what it says: monitor context levels and save checkpoints to memory files. Before installing: (1) confirm what 'memory/' directory the agent will use and that the skill is restricted to that path (avoid giving it open filesystem read access); (2) ensure session_status exists and returns contextTokens as expected; (3) review what kinds of information will be saved (decisions, pending tasks, file paths) and avoid storing secrets or credentials in checkpoints; (4) consider access controls or encryption for the memory folder if checkpoint files could contain sensitive data; (5) if you want stricter behavior, ask for the skill to explicitly limit reads to its memory file and not enumerate or read arbitrary system files.

Type: OpenClaw Skill Name: session-watchdog Version: 1.0.0 The skill bundle is designed to help the AI agent manage its own session context and memory, proactively saving checkpoints. All instructions in SKILL.md are focused on self-management, such as checking `session_status`, reading/writing to a designated 'memory file' (e.g., `memory/YYYY-MM-DD.md`) for checkpointing, and interacting with the user about context levels. There is no evidence of prompt injection attempting to subvert the agent, exfiltrate data, execute arbitrary commands, or perform any other malicious actions. The file operations are confined to the agent's own memory management, which is a legitimate function for this type of skill.