strategic-compact

原文涵盖的主题

• Strategic Compact Skill
• When to Activate
• Why Strategic Compaction?
• How It Works
• Hook Setup
• Configuration
• Compaction Decision Guide
• What Survives Compaction

Suggests manual /compact at strategic points in your workflow rather than relying on arbitrary auto-compaction. Running long sessions that approach context limits (200K+ tokens) Working on multi-phase tasks (research → plan → implement → test) Switching between unrelated tasks within the same session After completing a major milestone and starting new work When responses slow down or become less coherent (context pressure) Auto-compaction triggers at arbitrary points: Often mid-task, losing important context No awareness of logical task boundaries Can interrupt complex multi-step operations Strategic compaction at logical boundaries: After exploration, before execution — Compact research context, keep implementation plan After completing a milestone — Fresh start for next phase Before major context shifts — Clear exploration context before different task The suggest-compact.js script runs on PreToolUse (Edit/Write) and combines two signals: 1. Context size (primary) — Reads the latest usage record from the session transcript (transcriptpath in the hook payload) and sums inputtokens + cachereadinputtokens + cachecreationinputtokens (the true context size of the turn). Suggests /comp

这里只展示节选，请以完整原文和当前要求为准。