skills.rest
freedom909
freedom909COMMUNITY
Explore all skills by this author →
GitHub

context-budget

Audits Claude Code context window consumption and produces prioritized token-savings recommendations.

Updated Mar 18, 2026
Search Tags:#optimization#claude code#MCP servers#context window#token estimation#token audit
One-click install
npx skills add https://github.com/freedom909/real-estate-saas --skill context-budget-freedom909
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/freedom909/real-estate-saas/tree/main/.trae/skills/context-budget
Command: npx skills add https://github.com/freedom909/real-estate-saas --skill context-budget-freedom909

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Claude Code sessions accumulate hidden token overhead from agents, skills, MCP servers, rules, and CLAUDE.md files, degrading performance and shrinking usable context without any visibility into where the budget goes. ## Core Features & Use Cases - Component Inventory: Scans agents, skills, rules, MCP server configs, and CLAUDE.md files to estimate per-component token consumption. - Issue Detection: Flags bloated agent descriptions, heavy files, redundant components, MCP over-subscription, and CLAUDE.md bloat. - Prioritized Report: Classifies components into keep/lazy-load/remove buckets and outputs a ranked savings report with a verbose per-file breakdown mode. - Use Case: Before adding five new MCP servers, run an audit to learn current overhead is 33% and that removing two CLI-replaceable servers first keeps you under a 40% overhead target. ## Quick Start Ask the assistant to run a context budget audit of the current Claude Code setup and report the top token-saving optimizations.

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 window usage?▼

Run the context-budget audit to scan agents, skills, rules, MCP servers, and CLAUDE.md files. It estimates tokens per component using word and character heuristics, then reports total overhead and ranked savings opportunities.

How much context do MCP servers consume in Claude Code?▼

Each MCP tool schema costs roughly 500 tokens, so a 30-tool server can exceed the cost of all installed skills combined. Servers wrapping simple CLI tools like gh, git, or npm are flagged as replaceable.

Why does my Claude Code session feel sluggish after adding skills?▼

Every agent description loads into each Task tool invocation, and every skill, rule, and MCP schema adds fixed overhead. An audit identifies heavy files over 200 lines and bloated descriptions over 30 words driving the slowdown.

Can I check context headroom before adding more MCP servers?▼

Yes, the pre-expansion check estimates current overhead percentage and projects the cost of new servers at roughly 500 tokens per tool. It recommends removals first if the addition would push overhead past a safe threshold.

What are the limitations of token estimation in a context audit?▼

Estimates use heuristics like words times 1.3 for prose and characters divided by 4 for code, not exact tokenizer counts. Results are directional for ranking optimizations rather than precise billing-grade measurements.

Related Skills

Explore More Software Engineering Skills→
JaimeJunrJaimeJunr
2

context-budget

Quantify token overhead across Claude Code agents, skills, MCP servers, and rules.

Community
Advanced
aayushsoamaayushsoam
1

context-budget

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

Community
Intermediate
PAISHU-AIPAISHU-AI

latency-critical-systems

Analyze p50, p95, and p99 latency metrics for real-time systems.

Community
Advanced
AlltwiceAlltwice

splines-list

Lists every SplineContainer in the active Unity scene with spline and knot counts.

Community
Basic