When is the best time to run the /context-budget command?

You should run it whenever you notice a decline in output quality, after installing new plugins, or before adding significant new resources to your environment.

How does the Context Budget skill estimate token usage?

It uses standard heuristics: prose is calculated at words multiplied by 1.3, while code-intensive files are estimated based on total characters divided by four.

Why does this skill flag MCP servers?

Each MCP tool schema typically consumes about 500 tokens. A server with many tools can easily exceed the overhead of all your other skills combined, making it a primary target for optimization.

Does it automatically delete my files?

No, it generates a comprehensive audit report with actionable suggestions, allowing you to choose which redundant components to remove or optimize.

Context Budget Manager

Name: Context Budget Manager
Author: affaan-m

byaffaan-m

•

172,008

•

Productivity & Workflow

Optimizes Claude Code performance by auditing and reducing token consumption across agents, skills, and MCP servers.

The Context Budget skill is a performance optimization tool designed to maintain high-quality AI outputs by managing Claude Code's context window. It scans all loaded components—including agents, skills, MCP servers, and rules—to identify bloat, redundancy, and unnecessary token overhead. By providing a detailed report and prioritized optimization suggestions, it helps developers reclaim context space, ensuring that the model remains fast and focused even in complex, multi-agent environments.

Key Features

01Detailed MCP server auditing to identify high-overhead tool schemas

02Automated token estimation for agents, skills, and rule files

03Prioritized optimization reports with estimated token savings

04172,008 GitHub stars

05Detection of redundant components and bloated agent descriptions

06Verbose analysis mode for file-level breakdowns and logic overlaps

Use Cases

01Planning context headroom before scaling up a project with new automated workflows

02Improving AI response quality and speed when the session feels sluggish

03Auditing the impact of adding new MCP servers or multiple specialized agents

Key Features

01Detailed MCP server auditing to identify high-overhead tool schemas

02Automated token estimation for agents, skills, and rule files

03Prioritized optimization reports with estimated token savings

04172,008 GitHub stars

05Detection of redundant components and bloated agent descriptions

06Verbose analysis mode for file-level breakdowns and logic overlaps

Use Cases

01Planning context headroom before scaling up a project with new automated workflows

02Improving AI response quality and speed when the session feels sluggish

03Auditing the impact of adding new MCP servers or multiple specialized agents