skills.rest
arbisoft
arbisoftOFFICIAL
Explore all skills by this author →
Website𝕏@arbisoftGitHub

context-budget

Audit token overhead in Claude Code sessions and generate a Context Budget Report.

4|7|Updated Apr 9, 2026
Search Tags:#performance#context#optimization#ai#claude#tokens#budget
One-click install
npx skills add https://github.com/arbisoft/ai-skillforge --skill context-budget-arbisoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/arbisoft/ai-skillforge/tree/main/Claude/skills/context-budget
Command: npx skills add https://github.com/arbisoft/ai-skillforge --skill context-budget-arbisoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits token overhead in Claude Code sessions to identify context bloat and optimize usage.

Core Features & Use Cases

  • Inventory-based token estimation across Agents (agents/.md), Skills (skills//SKILL.md), Rules (rules/**/*.md), and MCP servers.
  • Classification into Always needed, Sometimes needed, and Rarely needed to guide on-demand activation.
  • Issue detection for bloated descriptions, heavy agents, redundant components, MCP over-subscription, and CLAUDE.md bloat.
  • Generation of a Context Budget Report with estimated token savings and prioritized optimizations.
  • Verbose mode for per-file debugging, cross-component overlap analysis, and MCP tool detail glimpses.
  • Pre-expansion checks to gauge impact of adding components and planning changes.

Quick Start

Run the /context-budget command to generate a live context budget report for your current Claude 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 Claude Code context usage to reduce token overhead?▼

To audit Claude Code context usage, generate a Context Budget Report that inventories tokens across agents, skills, rules, and MCP servers. This report classifies components by necessity and flags bloated descriptions to identify context bloat and prioritize savings.

What causes high token consumption in Claude AI sessions?▼

High token consumption in Claude AI sessions is caused by context bloat from heavy agents, redundant components, excessive MCP tool counts, and bloated CLAUDE.md files. Auditing these areas classifies usage into always, sometimes, or rarely needed categories.

Can I check the context budget impact before adding new MCP servers?▼

You can check the context budget impact before adding new MCP servers by running a pre-expansion check. This estimates the token overhead of new components and identifies potential MCP over-subscription issues before onboarding them into the session.

How do I optimize AI agent descriptions to save tokens?▼

To optimize AI agent descriptions and save tokens, run a context audit to detect bloated descriptions and heavy agents. The generated report provides cross-component overlap analysis and prioritized optimizations for reducing token overhead.

Does the context audit work for troubleshooting Claude performance issues?▼

The context audit works for troubleshooting Claude performance issues by surfacing verbose mode per-file debugging and cross-component overlap analysis. It flags excessive MCP tool counts and CLAUDE.md bloat that degrade session performance.

Related Skills

Explore More Software Engineering Skills→
oimiragieooimiragieo
36

mcp-converter

Convert MCP servers with 10+ tools into Claude Skills.

Community
Advanced
nassimbfnassimbf
3

context-budget

Audit Claude Code context window usage across agents, skills, MCP servers, and rules.

Community
Advanced
istinataFTSistinataFTS
2

caveman-stats

Analyze Claude Code session JSONL logs for token usage and savings.

Community
Basic
ZESCODEZESCODE

context-budget

Audit token consumption across agents, skills, rules, and MCP servers.

Community
Intermediate