Verified:GitHub

context-compression

Compress large conversation histories and codebases exceeding context window limits.

1|Updated Feb 4, 2026

Search Tags:#summarization #codebase analysis #token optimization #agent memory #context compression #long-running sessions

Ready to run

npx skills add https://github.com/bthillerup/bens-garage-session-2 --skill context-compression-bthillerup

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-compression
Source: https://github.com/bthillerup/bens-garage-session-2/tree/main/.github/skills/context-compression
Command: npx skills add https://github.com/bthillerup/bens-garage-session-2 --skill context-compression-bthillerup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill addresses the challenge of managing large conversation histories and codebases that exceed context window limits, preventing agents from "forgetting" critical information and ensuring efficient token usage.

Core Features & Use Cases

Context Management: Implements strategies to compress and summarize conversation history or large code contexts.
Token Efficiency: Reduces token usage per request and optimizes tokens per task for long-running agent sessions.
Use Case: When working on a large codebase that exceeds the AI's context window, this skill can be used to summarize the relevant parts of the code and conversation history, allowing the agent to continue working effectively without losing track of previous changes or instructions.

Quick Start

Use the context-compression skill to summarize the last 5000 tokens of the conversation history.

Frequently Asked Questions about context-compression

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

FAQPage Schema

How do I compress conversation history when it exceeds the context window limit?▼

Context compression reduces token consumption by applying anchored iterative summarization or opaque compression techniques to large conversation histories. This maintains agent memory and prevents critical information loss when sessions exceed context window limits.

What is the best way to analyze a large codebase that exceeds the AI context window?▼

Large codebase analysis requires structured summarization of relevant code and conversation history. By compressing context into manageable summaries, agents maintain track of previous changes and instructions while continuing to work effectively without hitting token limits.

When do I need context compression for long-running agent sessions?▼

Context compression is needed when long-running agent sessions accumulate histories exceeding context window limits. Without compression, agents forget critical information and waste tokens, making structured summarization essential for maintaining efficient memory.

How does anchored iterative summarization work for managing agent memory?▼

Anchored iterative summarization compresses conversation history by repeatedly summarizing prior context windows into structured summaries. This technique maintains agent memory across long-running sessions while significantly reducing per-request token consumption.

Can I summarize the last 5000 tokens of a conversation history to optimize tokens per task?▼

Yes, summarizing specific token ranges like the last 5000 tokens of conversation history is a supported context compression strategy. This reduces token usage per request and optimizes overall tokens per task for long-running agent sessions.

Does context compression work with large-scale codebase analysis tasks?▼

Context compression applies directly to large-scale codebase analysis by summarizing relevant code parts and conversation histories. This allows agents to continue working effectively on codebases exceeding context window limits without losing track of instructions.