strategic-compact

Suggest manual context compaction after a configurable threshold of tool calls.

Updated Jan 24, 2026
One-click install
npx skills add https://github.com/Lincyaw/cc-md --skill strategic-compact-lincyaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: strategic-compact
Source: https://github.com/Lincyaw/cc-md/tree/main/skills/strategic-compact
Command: npx skills add https://github.com/Lincyaw/cc-md --skill strategic-compact-lincyaw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps manage Claude's context window by suggesting manual compaction at logical points in a workflow, preventing the loss of important information due to arbitrary auto-compaction.

Core Features & Use Cases

  • Strategic Compaction: Prompts users to manually compact context at key task boundaries (e.g., after exploration, before execution).
  • Threshold-Based Suggestions: Offers reminders to compact based on a configurable number of tool calls.
  • Use Case: When working on a complex project, you might explore many different approaches. Before you start coding the chosen solution, this skill will remind you to compact your research context, keeping only the essential plan.

Quick Start

Use the strategic-compact skill to suggest manual context compaction when transitioning between task phases.

Frequently Asked Questions about strategic-compact

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

FAQPage Schema
How do I prevent Claude's context window from losing important information during auto-compaction?

Manual context compaction at logical task boundaries prevents losing important information during auto-compaction. By prompting you to compact after configurable tool call thresholds, it preserves essential context across task phases.

When should I manually compact context instead of relying on automatic compaction?

You should manually compact context at key task boundaries, such as after exploration and before execution. This strategic compaction retains essential plans and research, avoiding arbitrary information loss from automatic triggers.

How do I track tool calls to trigger manual context compaction in Claude?

You track tool calls to trigger manual context compaction using a shell script provided by the skill. This script monitors tool invocations and prompts you to compact after reaching a configurable threshold.

Does manual context management require any specific dependencies or setup?

Manual context management requires no external dependencies, only a shell script to monitor tool invocations. You configure the threshold for tool usage, and the script provides timely suggestions to compact.

What is the best way to manage token usage during complex workflows with multiple tool calls?

The best way to manage token usage during complex workflows is threshold-based context compaction. Tracking tool calls and prompting strategic compaction at task phase transitions optimizes memory and preserves essential context.

Why does arbitrary auto-compaction cause problems in long coding tasks?

Arbitrary auto-compaction causes problems by discarding vital context mid-task. Strategic compaction suggests manual context preservation at logical intervals, ensuring research and execution plans survive throughout the workflow.