context-budget

Name: context-budget
Availability: InStock
Author: Zardus

Audit token overhead across loaded Claude Code components and output prioritized savings.

1|1|Updated Mar 31, 2026

Search Tags:#context #optimization #skills #agents #mcp #budget #token

Ready to run

npx skills add https://github.com/zardusai-cyber/zardus_setup --skill context-budget-zardusai-cyber

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/zardusai-cyber/zardus_setup/tree/main/ecc/skills/context-budget
Command: npx skills add https://github.com/zardusai-cyber/zardus_setup --skill context-budget-zardusai-cyber

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits token overhead across every loaded component in a Claude Code session to identify bloat and surface actionable token-savings recommendations.

Core Features & Use Cases

Analyze token usage across Agents, Skills, Rules, MCP servers, and CLAUDE.md chains to surface optimization opportunities.
Flag heavy agents, bloated SKILLs, redundant components, and MCP over-subscription to guide targeted cleanup.
Use the /context-budget command to run a full audit and prioritize savings.

Quick Start

Run /context-budget to generate a token-savings report for my current Claude Code setup.

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 when many agents and MCP servers are loaded?▼

To reduce token usage in Claude Code, you can run a context audit to scan loaded Agents, Skills, Rules, MCP servers, and CLAUDE.md chains. This identifies bloated components and outputs prioritized token-saving actions.

Why does Claude Code performance degrade when multiple MCP servers and skills are active?▼

Claude Code performance degrades because active MCP servers and skills consume token overhead in your session context. Auditing this overhead flags redundant components and MCP over-subscription to guide targeted cleanup.

What is the best way to audit context window bloat across Claude Code components?▼

The best way to audit context window bloat is to scan all loaded components including Agents, SKILL.md files, and CLAUDE.md chains. This surfaces heavy agents and redundant components to guide optimization.

How do I identify which MCP servers or agents are consuming the most tokens?▼

You can identify high token consumption by running a full context audit that analyzes token usage across all loaded MCP servers, agents, and rules. The audit flags heavy agents and MCP over-subscription for targeted cleanup.

Can I optimize my CLAUDE.md chain and rules to reclaim context tokens?▼

Yes, you can optimize your CLAUDE.md chain and rules to reclaim context tokens by scanning them for overhead. The audit analyzes these components alongside skills and agents to surface actionable token-savings recommendations.

When should I run a token overhead audit on my Claude Code session?▼

You should run a token overhead audit when many agents, skills, or MCP servers are present or when session performance degrades. The audit generates a token-savings report to prioritize maintenance and optimization.