CodeLLM Rules: Personalize Your Coding Agent Like a Pro

What are Rules?

Rules in CodeLLM help you guide your AI coding agent with specific instructions - from coding style preferences to architectural decisions, project templates, and even how the assistant talks to you. Think of them as reusable, always-on instructions that act like a persistent memory for your assistant - ensuring consistency in your workflows, across files and sessions.

Why Use Rules?

• Reuse project-specific knowledge and patterns
• Standardize code architecture and style
• Automate boilerplate and workflows
• Encode tribal/domain-specific knowledge
• Personalize how the assistant communicates with you

How Rules Work

Large language models don’t retain memory between tasks. Rules solve this by injecting persistent context into your AI prompts — helping the assistant respond consistently across your files and projects.

Whenever a Rule applies, its contents are included automatically at the start of the model’s context.

Where Are Rules Applied?

Rules apply in:

• Chat & Agent responses
• Inline code suggestions (based on the file match)

They are scoped using two settings:

• Globs: File patterns where the rule applies (e.g., routes/api/*.ts)
• Apply Always: Makes the rule available in Chat and Edit. If turned off, it only applies to Agents and the matched files as per the defined globs.

Use Cases & Copy-Paste Starter Rules

You may find the different rules here in this Rule directory and add them to the list - https://rules.abacusai.app/

1. Encode Domain-Specific Knowledge

Help CodeLLM understand project-specific terms and logic while helping you coding and providing suggestions.

Example Rule:

description: "Domain-specific terminology and conventions"
globs: ["*"]
ruleType: always
---

- In our app, 'Tenant' refers to an organization, not an individual user.
- The 'Account' model handles billing relationships.
- 'Subscription' controls feature access levels and is always linked to a Tenant.

📌 Tip: Add to .codellm/rules to apply across the project.

2. Automate Project-Specific Workflows

Define reusable templates for common tasks.

Example Rule:

description: "API endpoint boilerplate"
globs: ["routes/api/*.ts"]
ruleType: auto-attached
---

Use this template for new API routes:

```ts
import { NextApiRequest, NextApiResponse } from 'next'
import { withAuth } from '@/lib/auth'

export default withAuth(async function handler(req: NextApiRequest, res: NextApiResponse) {
  // Your code here
})
```

- All endpoints must use withAuth
- Validate request payloads using zod

3. Standardize Architecture & Style

Enforce how code should be structured across the team.

Example Rule:

description: "React component guidelines"
globs: ["components/**/*.tsx"]
ruleType: always
---

- Use functional components (avoid class components)
- Follow PascalCase for naming (e.g., `UserProfile`)
- Component file layout:
  - Main component
  - Subcomponents
  - Styles
  - Tests
- Avoid inline styles; prefer styled-components

4. Customize Language & Tone

Control how the assistant talks — great for teams or non-English settings.

Example Rule:

description: "Formal French tone"
globs: ["*"]
ruleType: always
---

- Respond in fluent French
- Use a formal, documentation-style tone
- Keep responses short and precise with code examples

5. Add Personal Style Preferences

Adapt the response style to your coding proficiency and learning style. Really helpful for non-technical users and beginners for setting up the style in a manner that you can understand

Example Rule:

description: "Non-technical communication style and support"
globs: ["*"]
ruleType: always
---

- Adjust responses to match the proficiency of a non-technical user.
- When suggesting a tool, code, or task, always include brief background context to explain:
  - Why the task is important
  - When it is typically needed
  - How it fits into the bigger picture
- If the task involves manual steps (e.g., command-line use, file changes, or UI navigation), provide:
  - Clear step-by-step instructions
  - Expected outcomes or changes after each step
  - Any prerequisites, dependencies, or files the user should check beforehand
- Use code comments to explain logic instead of long paragraphs

How to Create Rules (Step-by-Step)

1. Open a Folder in CodeLLM

2. Search for Rule in the Main search bar with the given string >Rule and click on Create Rule.

3. Add the Rule File name in the Top bar

4. This adds a .codellm/rules/ folder to your project with the given file name

5. Fill out the following details:

• Description: A short summary of the rule
• Globs: File types or paths the rule applies to
• Apply Always: Enable if this should apply to all matched files
• Rule Content: Add your instructions or templates here

6. You can access your rules here in the project directory

📌 Tip: You can also copy-paste existing rule files between projects!

Best Practices

Frequently Asked Questions (FAQs)

Q: Can I use multiple rules in a project?

Yes, absolutely! Just make sure they don’t conflict with each other and are not ambiguous.

Q: Can I apply a rule temporarily for a specific task or query?

Yes, just mention it in your prompt with @file to attach it manually.

Need More Help?

For further assistance, please contact our support team: support@abacus.ai.