Anti-Amnesia Agent
ReviewAudited by ClawScan on May 10, 2026.
Overview
This is a coherent memory skill, but it asks the agent to automatically save and reuse nearly all session content without clear limits or retention controls.
Install only if you are comfortable with conversation history and decisions being written to persistent workspace files. Keep the memory directory private, avoid sharing it or committing it to version control, redact secrets, and define cleanup rules before enabling the automatic hook.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Sensitive chats, secrets, business details, or mistaken instructions may be stored in workspace memory and influence later sessions.
The skill automatically persists broad conversation history and then makes those files recurring authoritative context, without artifact guidance on exclusions, redaction, retention, or user approval.
"Automatically saves full conversation"; "messages": 9999; "Daily Journals ... capture everything"; "STATE.md — Single source of truth"
Use only in trusted private workspaces; reduce the saved-message limit, exclude or redact secrets, add retention and cleanup rules, and review memory files before treating them as authoritative.
The agent may inspect local OpenClaw cron and gateway state as part of its routine heartbeat.
The heartbeat template asks the agent to run local status checks on wake-up. These appear read-only and aligned with health monitoring, but users should notice the recurring local tool use.
`cron list` → check **consecutiveErrors > 0**; `openclaw gateway status` → running?
Confirm those checks are appropriate for the workspace and keep any added process checks read-only unless you explicitly approve changes.