context-budget

Quantify token overhead across Copilot CLI components and output prioritized recommendations.

Updated Mar 26, 2026

Search Tags:#performance #optimization #audit #context-window #copilot-cli #context-budget #token-overhead

Ready to run

npx skills add https://github.com/RogerioSobrinho/codeme-copilot --skill context-budget-rogeriosobrinho

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/RogerioSobrinho/codeme-copilot/tree/main/skills/context-budget
Command: npx skills add https://github.com/RogerioSobrinho/codeme-copilot --skill context-budget-rogeriosobrinho

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits Copilot CLI context window consumption across agents, skills, MCP servers, and rules. Identifies bloat and produces prioritized token-savings recommendations.

Core Features & Use Cases

Inventory-based analysis of context overhead across agents, skills, rules, MCP servers, and CLAUDE.md chains.
Generates prioritized token-savings recommendations and actionable optimizations.
Use cases include preparing for new skill deployments, diagnosing performance slowdowns, and planning context budget.

Quick Start

Run the /context-budget command to generate a full context budget report for your current Claude Code session.

Frequently Asked Questions about context-budget

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

FAQPage Schema

How do I audit Copilot CLI context window token overhead?▼

To audit Copilot CLI context window token overhead, run the /context-budget command. It inventories all loaded agents, skills, rules, MCP servers, and CLAUDE.md chains to quantify token consumption and flag heavy files.

Why does my Copilot CLI session run slowly with many active skills?▼

Your Copilot CLI session runs slowly due to context window bloat from loaded components. This Skill identifies token overhead across agents, skills, rules, and MCP servers, then outputs prioritized recommendations to optimize context headroom.

What is the best way to plan context budget before deploying new agents?▼

The best way to plan context budget before deploying new agents is to inventory existing token overhead. This Skill counts tokens per component and applies estimation rules to reveal available context headroom for new deployments.

Can I identify which MCP servers or CLAUDE.md chains cause context bloat?▼

Yes, you can identify which MCP servers or CLAUDE.md chains cause context bloat. The Skill performs inventory-based analysis across all Copilot CLI components, counting tokens per file and flagging heavy files for optimization.

Do I need any dependencies to analyze token consumption in Claude Code?▼

No dependencies are required to analyze token consumption in Claude Code. The Skill operates independently using built-in token estimation rules to audit context window consumption and generate actionable optimizations.