AI & Machine Learning

Session Guard

Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts ignoring rules it followed earlier, when conventions drift, when output quality seems to degrade, or after any context compaction event. Prevents long-session corruption AND context compaction amnesia through behavioral self-enforcement.

Publisher / source
wshobson/agents (found on skills.sh, the CSV list)
Upstream record
wshobson/agents
Version
Version 3
Published
Publication review
Approved for publication · recorded passed scan 2026-11-02
Content fingerprint
2bdc028582d5a6b818155153ec27e23c0fa088a65b8fbe09278927dfdbce72ce