budget-guard

Checks token budgets across query, session, and monthly tiers before AI operations.

2|Updated Apr 8, 2026

Search Tags:#rate limiting #budget #approval #preflight #token #gateway

Ready to run

npx skills add https://github.com/DojoGenesis/gateway --skill budget-guard

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: budget-guard
Source: https://github.com/DojoGenesis/gateway/tree/main/plugins/system-health/skills/budget-guard
Command: npx skills add https://github.com/DojoGenesis/gateway --skill budget-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents costly overruns by evaluating remaining token budgets across query, session, and monthly tiers before an expensive AI operation proceeds.

Core Features & Use Cases

Multi‑tier Budget Evaluation: Queries query, session, and monthly token limits in a single call.
Category‑Based Cost Multipliers: Adjusts estimated token usage based on operation type (web, compute, file, memory).
Decision Matrix: Returns APPROVE, WARN, or BLOCK decisions with detailed utilization metrics.
Use Cases: Pre‑flight checks for web searches, heavy compute tasks, file processing pipelines, or any multi‑step AI workflow that could exceed token budgets.

Quick Start

Ask the budget guard to verify if a 2,000‑token web search fits within the current budget.

Frequently Asked Questions about budget-guard

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

FAQPage Schema

How do I check token budget limits before running an expensive AI operation?▼

To check token budget limits before an expensive AI operation, evaluate remaining allowances across query, session, and monthly tiers using a pre-flight validation gate. The system returns APPROVE, WARN, or BLOCK decisions based on utilization thresholds.

What is a pre-flight token budget check and when do I need it?▼

A pre-flight token budget check prevents costly overruns by evaluating remaining token allowances before expensive operations like web searches, compute tasks, or file processing proceed. You need it for multi-step AI workflows that risk exceeding defined token limits.

Can I apply different cost multipliers for web, compute, and file operations?▼

You can apply category-based cost multipliers to adjust estimated token usage based on operation type, including web, compute, file, or memory tasks. This adjusts the pre-flight evaluation to reflect the true cost of the specific AI action.

How do I enforce rate limiting and block actions that exceed session token limits?▼

You enforce rate limiting by evaluating token utilization against configured thresholds in a pre-flight check. The system returns a BLOCK decision if the estimated usage exceeds session or monthly token limits, halting the operation before it runs.

Does the pre-flight budget check work for multi-step AI workflows?▼

The pre-flight budget check works for multi-step AI workflows by evaluating remaining token budgets across query, session, and monthly tiers. It ensures cumulative token usage from sequential tasks like file processing pipelines remains within defined limits.

What is the difference between APPROVE, WARN, and BLOCK decisions in token budgeting?▼

The difference between APPROVE, WARN, and BLOCK decisions in token budgeting lies in utilization thresholds: APPROVE allows the operation, WARN indicates approaching limits, and BLOCK prevents execution when estimated token usage exceeds the remaining budget.