context-budget

Audit token overhead across loaded Claude Code session components.

Updated Mar 31, 2026

Search Tags:#performance #optimization #audit #claude-code #context-budget #token-overhead

Ready to run

npx skills add https://github.com/GGEdu/claude-god-mode-template --skill context-budget-ggedu

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/GGEdu/claude-god-mode-template/tree/main/skills/context-budget
Command: npx skills add https://github.com/GGEdu/claude-god-mode-template --skill context-budget-ggedu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits and reduces token overhead across Claude Code sessions by analyzing all loaded components (agents, skills, rules, MCP servers, CLAUDE.md) and surfacing bloats, redundancies, and actionable token-savings recommendations.

Core Features & Use Cases

Inventory and token estimation for Agents, Skills, Rules, MCP servers, and CLAUDE.md to quantify context load.
Flagging criteria to identify heavy files, bloated frontmatter, and overlapping content across components.
Phase-based Context Budget reporting that outputs a prioritized set of optimizations with potential token savings and actionable next steps.
Use Case: When many skills or servers are added, run this Skill to quickly reveal top opportunities to reclaim context space and improve session performance.

Quick Start

Run the context-budget analysis to produce a 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 context bloat from loaded skills and MCP servers?▼

Reduce Claude Code context bloat by running a context-budget audit to inventory all loaded agents, skills, rules, and MCP servers. This surfaces redundancies and generates a prioritized Context Budget Report with actionable token-saving recommendations to reclaim session space.

What is the best way to audit token overhead across a Claude Code session?▼

Auditing token overhead across a Claude Code session involves counting tokens per file, flagging heavy items, and detecting overlapping content across all loaded components like CLAUDE.md and MCP servers. It outputs a phase-based Context Budget Report detailing potential token savings.

How can I check if my CLAUDE.md or MCP servers are consuming too many tokens?▼

Check whether your CLAUDE.md or MCP servers consume too many tokens by applying flagging criteria designed to identify bloated frontmatter and heavy files. The analysis quantifies context load per component to reveal which specific items are taking up excessive space.

When do I need to run a token optimization audit for my Claude Code agents?▼

Run a token optimization audit for your Claude Code agents when many skills or servers are added to your environment and session performance degrades. The audit quickly reveals top opportunities to reclaim context space by surfacing bloats and overlapping content.

Can I detect overlapping content and redundancies across multiple Claude Code rules?▼

Detect overlapping content and redundancies across multiple Claude Code rules by running a context-budget analysis. It inventories all loaded components, detects content overlaps, and generates recommended optimizations to eliminate redundant token overhead.

What components does a context budget report analyze to improve session performance?▼

A context budget report analyzes agents, skills, rules, MCP servers, and CLAUDE.md files to improve session performance. It quantifies context load, flags heavy items, and outputs a prioritized set of optimizations with potential token savings and actionable next steps.