What it does
The skill describes a working loop for agentmemory sessions. Before starting work, the agent recalls what is already stored. At decision points it saves what was settled, and it learns from corrections it receives. The publisher also gives guidance on judging whether a given item belongs in memory at all.
It is intended for nontrivial tasks, for moments after a decision is settled or a debugging gotcha is resolved, and for any point where the agent is unsure whether something should be saved. The skill is distributed as part of the agentmemory plugin and is licensed under Apache-2.0.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 1
memory-discipline
The session loop that makes agentmemory pay off, recall before starting work, save at decision points, learn from corrections. Use when starting a nontrivial task, after settling a decision or debugging a gotcha, or whenever deciding if something belongs in memory.
As shown on www.aitmpl.com when we last read it