skills.rest
JansenAnalytics
JansenAnalyticsCOMMUNITY
Explore all skills by this author →
GitHub

budget

Rank token consumption of context files and skill descriptions.

5|Updated Apr 8, 2026
Search Tags:#context#analysis#tokens#budget#ranking#cost
One-click install
npx skills add https://github.com/JansenAnalytics/claudex --skill budget-jansenanalytics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: budget
Source: https://github.com/JansenAnalytics/claudex/tree/main/skills/budget
Command: npx skills add https://github.com/JansenAnalytics/claudex --skill budget-jansenanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The Budget skill provides visibility into how much of the session context is consumed by CLAUDE.md, memory, user profile, and the auto-loaded skill descriptions, helping you identify and prune context bloat.

Core Features & Use Cases

  • Exact ranking of the heaviest context sources based on token counts, including skill descriptions via skill-index.json.
  • Token-aware budgeting that surfaces bloat and informs pruning decisions, with optional cost data when available.
  • Use Case: diagnose slowdowns or token overflows by identifying top offenders in the current session.

Quick Start

Run budget.py to view the ranked context budget and identify items to prune.

Frequently Asked Questions about budget

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

FAQPage Schema
How do I check what is consuming my context window tokens in a session?▼

You can identify context bloat by parsing CLAUDE.md, MEMORY.md, USER.md, and skill-index.json to compute exact token rankings. This reveals which auto-loaded skill descriptions or configuration files are the heaviest offenders in your session.

Why does my session context overflow when loading multiple skills and memory files?▼

Session context overflows when CLAUDE.md, MEMORY.md, and 162 auto-loaded skill descriptions exceed the token limit. Parsing skill-index.json and configuration files provides an exact ranked spend report to diagnose which components cause the overflow.

How do I rank token weight distribution for auto-loaded skill descriptions?▼

You can rank token weight distribution by parsing skill-index.json alongside CLAUDE.md and .claude/rules/*.md files. This computes exact token counts for the 162 auto-loaded skill descriptions and presents them heaviest-first.

Can I estimate the cost of context window bloat from configuration files?▼

Yes, you can estimate context bloat costs by running budget.py to compute token counts for CLAUDE.md, MEMORY.md, and tool schemas. It presents an optional real-spend report that surfaces cost data to inform token-aware pruning decisions.

What is the best way to diagnose slowdowns caused by high token usage in session files?▼

The best way to diagnose token usage slowdowns is to run budget.py, which ranks context window consumption across CLAUDE.md, MEMORY.md, USER.md, and tool schemas. Identifying these top offenders allows you to prune bloat and resolve slowdowns.

Related Skills

Explore More Data & Analytics Skills→
slavochek2slavochek2
1

claude-md

Validate proposed CLAUDE.md changes for placement, redundancy, and universality.

Community
Advanced
Ruya-AIRuya-AI
368

diagnose

Analyze Claude Code session files for token counts and context usage.

Official
Intermediate
KyleKingKyleKing
3

skill-sync

Generate tool-specific configuration files referencing Claude Skills for AI coding tools.

Community
Intermediate
Michae2xlMichae2xl

context-budget

Audit Claude Code context window token consumption and generate prioritized savings recommendations.

Community
Advanced