memory
Two-layer memory system with grep-based recall.
Install
npx skillscat add goldengrape/agent-company/memory Install via the SkillsCat registry.
We need to produce a 2-3 sentence plain-text summary, objective, factual, no marketing, no superlatives, no calls to action, natural prose, no bullet points, no headings, no markdown. At most 60 words. No quotes. Just the summary text. We need to explain what the skill does: two-layer memory system with grep-based recall. Problem it solves: need to retain long-term facts and searchable event history without overloading context. When to use: when agent needs persistent memory across sessions, wants quick recall of past events via grep, wants automatic consolidation.
Memory
Structure
memory/MEMORY.md— Long-term facts (preferences, project context, relationships). Always loaded into your context.memory/HISTORY.md— Append-only event log. NOT loaded into context. Search it with grep.
Search Past Events
grep -i "keyword" memory/HISTORY.mdUse the exec tool to run grep. Combine patterns: grep -iE "meeting|deadline" memory/HISTORY.md
When to Update MEMORY.md
Write important facts immediately using edit_file or write_file:
- User preferences ("I prefer dark mode")
- Project context ("The API uses OAuth2")
- Relationships ("Alice is the project lead")
Auto-consolidation
Old conversations are automatically summarized and appended to HISTORY.md when the session grows large. Long-term facts are extracted to MEMORY.md. You don't need to manage this.
Categories
Install
npx skillscat add goldengrape/agent-company/memory Install via the SkillsCat registry.