token-budget-advisor

Prompt users to select a depth level before generating responses.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/GGEdu/claude-god-mode-template --skill token-budget-advisor-ggedu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: token-budget-advisor
Source: https://github.com/GGEdu/claude-god-mode-template/tree/main/skills/token-budget-advisor
Command: npx skills add https://github.com/GGEdu/claude-god-mode-template --skill token-budget-advisor-ggedu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Controls the length and depth of AI responses by prompting the user to select a token-budget or output level before answering.

Core Features & Use Cases

  • Upfront depth prompting: present options to choose Essential, Moderate, Detailed, or Exhaustive before generating a reply.
  • Token-budget estimation: uses heuristics to estimate input tokens and project the likely response window.
  • Session guardrails: respects an already-set depth level within the current conversation.

Quick Start

Offer the user a depth-level choice before generating the reply.

Frequently Asked Questions about token-budget-advisor

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

FAQPage Schema
How do I control response depth and token length before generating an AI reply?

To control response depth, you can prompt the user to select a predefined output level before generating the reply. This mechanism uses heuristic token estimation to project the response window and limits conversational detail accordingly.

What are the available output levels for managing AI response complexity?

The available output levels for managing AI response complexity are Essential, Moderate, Detailed, and Exhaustive. These predefined depth levels allow you to expand or limit the detail and length of conversational replies.

Can I set a session-wide response depth level to avoid repeated prompts?

Yes, you can set a session-wide response depth level. The system uses a gating mechanism that respects an already-set depth level within the current conversation, preventing repeated prompts for subsequent inquiries.

How does token-budget estimation work for conversational design?

Token-budget estimation for conversational design works by applying heuristics to estimate input tokens. It projects the likely response window based on the selected depth level before the AI generates its answer.

Does limiting response depth apply to code-related interactions and explanations?

Yes, limiting response depth applies to code-related interactions and explanations. The depth selection mechanism works across general inquiries, explanations, and code interactions to control detail and complexity.

What is the best way to reduce token usage in AI conversations?

The best way to reduce token usage in AI conversations is implementing an upfront depth prompt. Asking the user to choose an output level before answering ensures the generated response stays within the desired token budget.