Optimize context window for AI agents using Context-Mode.

In this article, we review Context-Mode. You will learn:

1. What is Context-Mode?

2. The problem

3. How Context Mode solves it

What is Context-Mode?

Context-Mode is the other half of the context problem — for developers and for engineering orgs. An MCP plugin that keeps raw data out of the LLM context window. A Platform that surfaces what your team is doing with the saved tokens. Same engine, two surfaces, your choice.

The problem

I read thru the context-mode README and found this problem statement which is accurate description of what goes into context window:

Every MCP tool call dumps raw data into your context window. A Playwright snapshot costs 56 KB. Twenty GitHub issues cost 59 KB. One access log — 45 KB. After 30 minutes, 40% of your context is gone. And when the agent compacts the conversation to free space, it forgets which files it was editing, what tasks are in progress, and what you last asked for. On top of that, the agent wastes output tokens on filler, pleasantries, and verbose explanations — burning context from both sides.

I mean tool call raw data can be heavy. I do use the Caveman, an open-source tool and skill designed for Caveman that strips filler words, pleasantries, and unnecessary phrasing from AI coding assistants like Claude Code to cut token usage by 65% to 75%. I configured it in my VS Code + Claude Code.

How Context Mode solves it

Context-Mode describes 4 sides of the problem:

1. Context Saving

2. Session Continuity

3. Think in Code

4. No prose-style enforcement

I did not quite understand what “Think in Code” meant here:

// Before: 47 × Read() = 700 KB.  After: 1 × ctx_execute() = 3.6 KB.
ctx_execute("javascript", `
  const files = fs.readdirSync('src').filter(f => f.endsWith('.ts'));
  files.forEach(f => console.log(f + ': ' + fs.readFileSync('src/'+f,'utf8').split('\\n').length + ' lines'));
`);

I mean you would want the contents of the file considered in the context window, not just the file names because file name alone does not tell you the entire story right?

Learn more about Context Mode.

About me:

Hey, my name is Ramu Narasinga. Email: ramu.narasinga@gmail.com

I spent 3+ years studying OSS codebases and wrote 400+ articles on what makes the production-grade. Now I'm putting that into practice differently - instead of writing every fix myself, I run coding agents that do it.

How it works? Register your machine as a Runtime, point it at your repo. Agents pick up issues. write the fix, open the PR. You just review, they execute.

Build your coding agents and get more work done in less time at thinkthroo.com

References:

1. github.com/mksglu/context-mode.

2. context-mode.com/ .

3. caveman.so/.