compact-discipline

Guide when to run /compact and resume from checkpoints.

8|1|Updated Mar 20, 2026

Search Tags:#prompt-engineering #context-management #memory-management #compact #ai-workflow #agent-teams #session-pruning

Ready to run

npx skills add https://github.com/ek33450505/claude-agent-team --skill compact-discipline

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: compact-discipline
Source: https://github.com/ek33450505/claude-agent-team/tree/main/skills/compact-discipline
Command: npx skills add https://github.com/ek33450505/claude-agent-team --skill compact-discipline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents context degradation in long-running AI sessions by prescribing when to run /compact and how to preserve essential history.

Core Features & Use Cases

Clear trigger rules for /compact based on context usage and session progress.
Checkpointing and resume guidance to preserve work and continuity.
CAST workflow integration for seamless adoption and automatic loading.
Use Case: When you hit context thresholds after exploring large datasets, compact to reclaim tokens without losing critical decisions.

Quick Start

Run /compact when your context usage nears the threshold to summarize and refresh the session, then resume from the updated checkpoint.

Frequently Asked Questions about compact-discipline

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

FAQPage Schema

How do I prevent context drift in long AI sessions?▼

To prevent context drift in long AI sessions, you need smart context management to prune history. Running /compact at strategic thresholds summarizes and refreshes the session, preventing degraded responses.

When should I run /compact to reclaim tokens during agent workflows?▼

You should run /compact to reclaim tokens when context usage nears thresholds after reading large files, during long explorations, or before beginning a new logical unit to prevent degraded responses.

How do I preserve critical decisions when pruning context history?▼

To preserve critical decisions when pruning context history, maintain a checkpoint before discarding data. This checkpointing ensures you can resume work seamlessly from the updated state after compaction.

What is the best way to manage context usage after exploring large datasets?▼

The best way to manage context usage after exploring large datasets is triggering /compact based on session progress. This prunes history and reclaims tokens without losing critical decisions made during exploration.

Can I resume my workflow automatically after running /compact?▼

Yes, you can resume your workflow after running /compact by following encoded operational requirements. The system provides resume guidance to continue from the updated checkpoint, ensuring continuity across agent teams.