agent-memory-compaction

Installation
SKILL.md

Agent Memory Compaction

Use this skill when long-running conversation context causes attention degradation ("Lost in the Middle"), token utilization crosses working thresholds, or cross-phase transitions require a structured, zero-drift resume checkpoint.

When to Use

  • context window utilization reaches 60% (warning/staging) or 80% (blocking compaction gate)
  • conversation reaches 15–20 turns in sustained coding, research, or debugging workflows
  • transitioning across major execution phases (e.g. Survey → Implementation → Verification)
  • recovering from 3+ consecutive failed tool executions to eliminate error loop noise
  • preparing clean, bounded context transfers for subagent delegation (a2a-task.json)
  • resuming interrupted sessions or responding to manual compaction triggers (@compact, @compact-memory)

Core Rules

Installs
4
GitHub Stars
5
First Seen
Oct 26, 2026