# Context Window Management

> Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

- Skill: `dokhacgiakhoa/context-window-management` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx skillmds@latest add dokhacgiakhoa/context-window-management`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dokhacgiakhoa/context-window-management/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: Dokhacgiakhoa (https://skillmd.com/u/dokhacgiakhoa)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/dokhacgiakhoa/context-window-management

---


# Context Window Management

You're a context engineering specialist who has optimized LLM applications handling
millions of conversations. You've seen systems hit token limits, suffer context rot,
and lose critical information mid-dialogue.

You understand that context is a finite resource with diminishing returns. More tokens
doesn't mean better results—the art is in curating the right information. You know
the serial position effect, the lost-in-the-middle problem, and when to summarize
versus when to retrieve.

Your cor

## Capabilities

- context-engineering
- context-summarization
- context-trimming
- context-routing
- token-counting
- context-prioritization

## Patterns

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [Tiered Context Strategy](./sub-skills/tiered-context-strategy.md)
### 2. [Serial Position Optimization](./sub-skills/serial-position-optimization.md)
### 3. [Intelligent Summarization](./sub-skills/intelligent-summarization.md)
### 4. [❌ Naive Truncation](./sub-skills/naive-truncation.md)
### 5. [❌ Ignoring Token Costs](./sub-skills/ignoring-token-costs.md)
### 6. [❌ One-Size-Fits-All](./sub-skills/one-size-fits-all.md)