How Neexo developers can reduce AI Credit usage through model selection, scoped prompts, small contexts, and monthly usage review.
AuthorNeexoCore
Updated
costai-creditsbilling
Core Principle
The expensive pattern is:
expensive model + large repository context + vague task
Avoid that combination.
Practical Rules
Use autocomplete for routine coding.
Use lightweight or default models for simple questions, small edits, and formatting.
Reserve stronger models for architecture, hard debugging, or high-risk review.
Give file or folder scope in every prompt.
Split large work into smaller sessions.
Use cost-conscious review prompts instead of broad repository review.
Monthly Review
Download the GitHub Copilot usage CSV and run the monthly usage review prompt from the Neexo Guardrails plugin. Look for top users, top models, outlier days, and agent sessions that used too much context.
Raw content
Copy this into your project — e.g. .instructions.md, .agent.md, or SKILL.md
## Core Principle
The expensive pattern is:
```text
expensive model + large repository context + vague task
```
Avoid that combination.
## Practical Rules
1. Use autocomplete for routine coding.
2. Use lightweight or default models for simple questions, small edits, and formatting.
3. Reserve stronger models for architecture, hard debugging, or high-risk review.
4. Give file or folder scope in every prompt.
5. Split large work into smaller sessions.
6. Use cost-conscious review prompts instead of broad repository review.
## Monthly Review
Download the GitHub Copilot usage CSV and run the monthly usage review prompt from the Neexo Guardrails plugin. Look for top users, top models, outlier days, and agent sessions that used too much context.