A framework for defining and enforcing custom behavioral guidelines and architectural constraints for AI coding agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install coding-agent-user-rules
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install coding-agent-user-rules using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Coding Agent User Rules?
Coding Agent User Rules is a specialized module within the Openclaw Skills directory designed to give developers granular control over how AI agents interact with their codebase. By providing a structured way to define 'rules of engagement,' this skill ensures that AI-generated code and suggestions remain consistent with specific project standards, security requirements, and architectural patterns.
Integrating this skill allows teams to minimize hallucinations and prevent the AI from making structural decisions that deviate from established norms. It serves as a vital governance layer for anyone leveraging Openclaw Skills to automate their development lifecycle.
Coding Agent User Rules Use Cases
- Enforcing project-specific naming conventions and folder structures across all AI-generated files.
- Restricting the use of certain libraries or APIs that are deprecated or forbidden in a secure environment.
- Providing project context and architectural guardrails to ensure the agent understands complex dependency trees.
- Standardizing the documentation style and comment requirements for every pull request generated by an agent.
How Coding Agent User Rules Works
- The user defines a set of JSON or YAML based instructions representing the project rules.
- The skill initializes within the Openclaw Skills runtime and loads the user-defined configuration.
- Every prompt or task sent to the AI coding agent is prepended or augmented with these behavioral constraints.
- The agent processes the task while maintaining compliance with the active rule set, ensuring outputs are project-ready.
Coding Agent User Rules Setup
To get started with this skill, install it via the CLI:
openclaw install coding-agent-user-rules
Once installed, navigate to your project root and create a configuration file to define your custom constraints for Openclaw Skills:
touch .openclaw-rules.json
Coding Agent User Rules Data Schema & Taxonomy
The skill manages rule definitions through a structured schema that allows for versioning and hierarchical enforcement:
| Attribute | Description | Required |
|---|---|---|
rule_id |
Unique identifier for the specific behavior constraint | Yes |
scope |
The directory or file type where the rule applies | Yes |
priority |
Integer determining which rule takes precedence in conflicts | No |
instruction |
The natural language description of the required behavior | Yes |
Coding Agent User Rules Advanced Features
- Path-based exclusion zones to prevent AI agents from modifying sensitive configuration files or legacy modules.
- Support for dynamic rule switching based on the current branch or environment context within Openclaw Skills.
- Recursive rule inheritance for monorepo setups where different packages require distinct coding standards.
- Integration with local linting results to provide real-time feedback loops to the agent during code generation.
SKILL.md
Loading
Related Openclaw Skills
Anthropic Brand Styling Skill
A professional styling utility that applies Anthropic's official brand identity, including specific color palettes and typography, to generated artifacts.
Algorithmic Art
Transform conceptual prompts into interactive, gallery-quality generative art using p5.js and computational philosophy.
WeCom Doc Fetcher
A specialized tool for converting WeChat Work developer documentation into clean, Obsidian-ready Markdown files using automated API fetching.
STM Assistant
A professional AI email assistant that manages outbound communication, branded signatures, and routing on behalf of a human user.
Dynamic Model Selector
An intelligent routing tool that selects the most efficient AI model for any given task within GitHub Copilot environments.
memory-sync
An automated tool to reconstruct and synchronize AI agent memory files by analyzing session logs and providing narrative summaries.
Featured*
