Context Scope Tags
PassAudited by ClawScan on May 1, 2026.
Overview
This is an instruction-only chat tagging convention with no code or credentials; its only notable aspect is user-directed memory/context signaling.
This skill appears safe to install as an instruction-only tag guide. Before relying on [REM] or [NOMEM], remember that actual memory behavior depends on your assistant platform, so use these tags together with the platform's memory controls.
Findings (1)
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.
If used with a memory-enabled assistant, the tags may influence whether information is reused across topics or saved for future chats.
The skill defines tags that influence cross-topic context reuse and long-term memory behavior. This is disclosed, user-directed, and central to the skill's stated purpose, but users should understand it can affect what context or preferences a memory-enabled agent carries forward.
`[GLOBAL]` cross-topic reuse allowed ... `[NOMEM]` do not store long-term memory ... `[REM]` persist preferences/decisions
Use [REM] only for preferences or decisions you actually want remembered, and use [ISO] or [NOMEM] for one-off or sensitive topics; also check the host agent's memory settings.