skills.rest
Femad-6
Femad-6COMMUNITY
Explore all skills by this author →
WebsiteGitHub

context-budget

Audits token consumption across agents, skills, MCP servers, and rules to recommend context savings.

Updated Mar 25, 2026
Search Tags:#optimization#claude code#agents#context window#mcp servers#token estimation#token audit
One-click install
npx skills add https://github.com/Femad-6/my-skills --skill context-budget-femad-6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-budget
Source: https://github.com/Femad-6/my-skills/tree/main/.github/skills/context-budget
Command: npx skills add https://github.com/Femad-6/my-skills --skill context-budget-femad-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Claude Code sessions accumulate context overhead from agents, skills, MCP servers, rules, and CLAUDE.md files, degrading performance and shrinking usable context. This Skill quantifies that overhead and identifies exactly which components to trim. ## 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 CLI-replaceable MCP servers. - Prioritized Report: Produces a ranked optimization report with estimated token savings per action and total potential savings. - Use Case: Before adding five new MCP servers, run an audit to learn that removing three CLI-replaceable servers frees ~27,500 tokens, keeping overhead under 40%. ## Quick Start Ask the assistant to run a context budget audit of the current setup and show 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 words times 1.3 for prose and produces a report ranking optimizations by token savings.

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 skills combined. Servers wrapping simple CLI tools like gh, git, or npm are flagged as replaceable to reclaim that overhead.

Why is my Claude Code session getting slower over time?▼

Accumulated agents, skills, MCP servers, and rules inflate every prompt's context, reducing effective headroom. Bloated agent descriptions load into every Task tool invocation even when the agent is never used.

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

Yes, the audit supports pre-expansion checks that estimate the token cost of planned additions against current overhead. It recommends removals first if the additions would push overhead past a reasonable 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, so figures are approximations rather than exact tokenizer counts. Duplicate skill copies are skipped to avoid double-counting, but actual runtime context may vary.

Related Skills

Explore More Software Engineering Skills→
pjherronpjherron

context-budget

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules.

Community
Intermediate
aayushsoamaayushsoam
1

context-budget

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

Community
Intermediate
rohitg00rohitg00
2.8k

context-optimizer

Diagnose and reduce token usage through compaction, MCP audits, and subagent delegation.

Community
Intermediate
rawvegrawveg
40

word-count-checker

Check document word counts with wc -w and report results.

Community
Basic