nap

Compress, prune, and archive agent context to reclaim memory.

3|3|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/quaid-app/quaid --skill nap-quaid-app
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nap
Source: https://github.com/quaid-app/quaid/tree/main/.copilot/skills/nap
Command: npx skills add https://github.com/quaid-app/quaid --skill nap-quaid-app

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reclaims context window budget by compressing agent histories, pruning old logs, archiving stale decisions, and cleaning orphaned inbox files.

Core Features & Use Cases

  • Context hygiene: compress histories and prune inbox artifacts to maintain memory efficiency.
  • Archive stale items: move old decisions and inbox files to secondary storage to reduce active state.
  • Use Case: Run before heavy fan-out tasks or after long-running sessions to keep memory usage in check.

Quick Start

Run squad nap to compress histories and prune inbox artifacts to reclaim memory.

Frequently Asked Questions about nap

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reclaim context window memory for agents with large histories?▼

Run context compression to compress agent histories and prune old logs. This reduces active memory usage during long-running campaigns or sessions with many agents using deterministic in-process cleanup operations.

What is context pruning and when should I archive agent state?▼

Context pruning compresses agent histories and archives stale decisions to reclaim memory. Run it before heavy fan-out tasks or after long-running sessions to maintain memory efficiency and reduce active state.

How do I clean up orphaned inbox files and stale agent decisions?▼

Clean up orphaned inbox files and stale decisions by archiving them to secondary storage. This reduces active state and reclaims memory budget using local, in-process threshold-based cleanup operations.

Does context archiving work for long-running multi-agent sessions?▼

Context archiving works for long-running multi-agent sessions by applying threshold-based cleanup to compress histories and move old decisions to secondary storage. Safe fallbacks ensure reliable in-process memory reclamation.

When should I not use deterministic context hygiene for memory reclamation?▼

Avoid deterministic context hygiene when you need to preserve full uncompressed agent histories or real-time access to every archived decision. The pruning process moves stale items to secondary storage, reducing active state availability.