context-budget

Audit token usage across Claude Code components to identify context bloat.

Updated Mar 20, 2026

Search Tags:#context #optimization #agents #mcp #budget #claude-code #token

Ready to run

npx skills add https://github.com/KanakMalpani/General-Private-Skills --skill context-budget-kanakmalpani

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/KanakMalpani/General-Private-Skills/tree/main/skills/context-budget
Command: npx skills add https://github.com/KanakMalpani/General-Private-Skills --skill context-budget-kanakmalpani

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits token overhead across every loaded component in a Claude Code session and surfaces actionable optimizations to reclaim context space.

Core Features & Use Cases

Inventory and quantify context headroom across Agents, Skills, Rules, MCP servers, and CLAUDE.md chains
Identify heavy files, duplicate content, and high-overhead tools to prioritize token savings
Provide prioritized recommendations to reduce context usage and boost session performance

Quick Start

Run /context-budget in your Claude Code session to generate an actionable token-savings report.

Frequently Asked Questions about context-budget

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

FAQPage Schema

How do I reduce token usage in Claude Code sessions?▼

To reduce token usage in Claude Code sessions, audit loaded agents, MCP servers, and CLAUDE.md chains to quantify available headroom and target high-overhead tools for removal.

What is context bloat and how does it affect Claude Code agents?▼

Context bloat in Claude Code agents is the accumulation of heavy files and redundant content that consumes token limits. It degrades session performance by reducing the available context headroom for active tasks.

How do I audit MCP server overhead in Claude Code?▼

You audit MCP server overhead in Claude Code by running an inventory command that quantifies token usage across all loaded components and identifies high-overhead tools for optimization.

Can I optimize context space when using many loaded skills and agents?▼

Yes, you can optimize context space with many loaded skills and agents by identifying duplicate content and heavy files, which surfaces actionable opportunities to reclaim token capacity and boost performance.

Why does my Claude Code session run out of context space?▼

Claude Code sessions run out of context space due to context bloat from redundant content, complex CLAUDE.md chains, and high-overhead MCP tools that rapidly consume available token limits.