Skip to content
Development
Command

/context-budget

Audit context window token consumption across all loaded components and recommend optimizations

From plugin
coco
22141 skills53 agents41 commands
Install
$ npx -y skills add coco-research/coco --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/context-budget

Context preview

What this command does when you run it.

Audit context window token consumption across all loaded components and recommend optimizations

Command definition

context-budget.md
description: "Audit context window token consumption across all loaded components and recommend optimizations"
allowed-tools:
  - Read
  - Bash
  - Glob
  - Grep

/context-budget — Token Consumption Audit

Run the context-budget skill to analyze token overhead across agents, skills, rules, MCP servers, and system prompts.

Usage

/context-budget              # Full audit
/context-budget --quick      # Summary only (top 5 savings)
/context-budget --verbose    # Include per-file breakdown

What It Does

1. Scans all component directories (agents/, skills/, rules/, MCP configs) 2. Estimates token count per component (words × 1.3 for text, × 1.5 for code) 3. Classifies each as Always/Sometimes/Rarely needed 4. Produces prioritized savings report with actionable recommendations

When to Run

  • Before adding new skills or agents
  • When session quality degrades mid-conversation
  • After installing a new system bundle (GSD, Brain, Team)
  • As part of `/team:ship` pre-flight checks
Ships withcoco

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 185 skills, 280 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.

Get the whole plugin

Other commands on coco.