context-budget

Audit token overhead across Claude Code sessions and flag bloated components.

1|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/aayushsoam/clawbot-plus --skill context-budget-aayushsoam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/aayushsoam/clawbot-plus/tree/main/skills/context-budget
Command: npx skills add https://github.com/aayushsoam/clawbot-plus --skill context-budget-aayushsoam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits token overhead across Claude Code sessions, identifying bloat and redundant components to reclaim context space and improve responsiveness.

Core Features & Use Cases

  • Inventory & analysis: scans agents, skills, rules, and MCP servers to estimate tokens and flag heavy components.
  • Prioritized optimizations: surfaces top token-saving actions and guidance for project-wide space reclamation.
  • Use Case: Run this when your Claude Code workspace grows with many skills and agents to restore available context headroom.

Quick Start

Invoke /context-budget to generate a live context budget report and recommended optimizations.

Frequently Asked Questions about context-budget

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

FAQPage Schema
How do I reduce Claude Code token overhead when loading many agents and MCP servers?

To reduce Claude Code token overhead, you can audit loaded agents, skills, rules, and MCP servers to estimate token usage and flag bloated components for removal or optimization.

Why does my Claude Code session run slow when many skills and rules are active?

Claude Code sessions run slow when numerous skills, rules, and MCP servers consume available context space, creating token bloat that degrades responsiveness and limits interaction headroom.

What is the best way to reclaim context space in a bloated AI agent workspace?

The best way to reclaim context space is running an inventory phase that scans all active components, estimates their token footprint, and surfaces prioritized actions to eliminate redundant rules or agents.

Can I audit token usage across specific MCP servers and custom rules in Claude Code?

Yes, you can audit token usage across specific MCP servers and custom rules by scanning the workspace to classify components and generate a live context budget report for optimization.

When should I run a context budget audit on my AI agent workspace?

You should run a context budget audit when your workspace grows heavily with many skills and agents, causing token overhead that impacts performance and requires reclaiming available context headroom.