Strategic Compact

Instead of letting Claude's auto-compaction fire mid-task and lose your context at the worst possible moment, this skill tracks your tool usage and suggests manual compaction at logical boundaries. It reminds you after 50 tool calls (configurable) to consider compacting, but leaves the decision to you. The real value is the decision guide: compact after research before implementation, compact after debugging, but never mid-implementation when you need all those variable names and file paths. It assumes you understand that TodoWrite and files persist through compaction but conversation context doesn't. Works best if you actually write important state to disk before compacting, which is the discipline this enforces.

skills.sh installs: 6.1K
GitHub stars: 229.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/everything-claude-code --skill strategic-compact --agent claude-code

Installs into .claude/skills of the current project.

Files

Strategic Compact Skill

Suggests manual /compact at strategic points in your workflow rather than relying on arbitrary auto-compaction.

When to Activate

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)

Why Strategic Compaction?

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