memory-manager

<!-- markdownlint-disable --> # Memory Manager Skill ## Overview This skill provides a standardized protocol for managing the project's persistent memory file (`memory.instructions.md`). It ensures that AI agents can reliably save and restore context across chat sessions, regardless of which instruction directory the project uses. This skill is **agent-agnostic** — any agent in the ecosystem can invoke it. The memory file is divided into **two distinct zones**: 1. **🧠 Knowledge Base** — A permanent section at the top that accumulates cross-session knowledge: architectural decisions, proven patterns, dead-ends with root causes, and key metrics. This section survives compaction and is never deleted. 2. **📝 Session Checkpoints** — Append-only entries at the bottom that track per-session progress. These are rotated during compaction, with valuable knowledge promoted to the Knowledge Base before deletion. For performance, the active memory path can be recorded in the project's `AGENTS.md` file as a fast-path shortcut. See **AGENTS.md Integration** below for details. ## When to Use - **Write Mode:** At the end of a significant milestone or phase completion, when the user agrees to save progress. - **Read Mode:** At the start of a new chat session to bootstrap context from prior sessions. - **Compaction Mode:** When the user requests cleanup of old checkpoints, promoting valuable knowledge to the Knowledge Base before deleting stale entries. --- ## Workflow 1: File Disco...