subagent-memory

What problem does it solve?

This Skill helps autonomous subagents retain useful context across invocations without letting their memory files become noisy, repetitive, or too large for prompt injection.

Core Features & Use Cases

• Reload Historical Context: Read MEMORY.md at the start of each task so the subagent can recall prior observations and repository-specific patterns.
• Chronological Observation Logging: Append dated bullets with priority emojis to capture critical lessons, useful facts, and completed milestones.
• Memory Compression: Run a reflection pass before the file approaches the harness limit so the most important knowledge stays compact and usable.
• Use Case: A long-running codebase analyzer can remember file paths, hard constraints, and prior discoveries across many separate runs without losing signal.

Quick Start

Tell the subagent to use subagent-memory so it rereads MEMORY.md, records new observations at task end, and compresses the file before it grows too large.