Coding Context CLI
A command-line interface for dynamically assembling context for AI coding agents.
This tool collects context from predefined rule files and task-specific prompts, substitutes parameters, and outputs a combined context to standard output. Use it to provide rich, relevant information to AI models like Claude, Gemini, or GPT.
Quick Example
# Install
sudo curl -fsL -o /usr/local/bin/coding-context \
https://github.com/kitproj/coding-context-cli/releases/download/v0.0.23/coding-context_v0.0.23_linux_amd64
sudo chmod +x /usr/local/bin/coding-context
# Use with an AI agent
coding-context -p issue_key=BUG-123 -s languages=go /fix-bug | llm -m claude-3-5-sonnet-20241022
Documentation Structure
This documentation follows the Diataxis framework, organized by your needs:
📚 Tutorials - Learning-oriented
Step-by-step guides to get you started:
- Getting Started Tutorial - Your first steps with the CLI
Best for: Learning the basics, first-time users, hands-on practice
🛠️ How-to Guides - Problem-oriented
Practical guides to solve specific problems:
- Create Task Files - Define what AI agents should do
- Create Rule Files - Provide reusable context
- Use Frontmatter Selectors - Filter rules and tasks
- Use Remote Directories - Load rules from Git, HTTP, or S3
- Use with AI Agents - Integrate with various AI tools
- Integrate with GitHub Actions - Automate with CI/CD
Best for: Solving specific problems, achieving specific goals, practical tasks
📖 Reference - Information-oriented
Technical specifications and API details:
- CLI Reference - Command-line options and arguments
- File Formats - Task and rule file specifications
- Search Paths - Where files are discovered
Best for: Looking up specific details, understanding options, technical specifications
💡 Explanation - Understanding-oriented
Conceptual guides to deepen your understanding:
- Agentic Workflows - Understanding autonomous AI workflows
- Architecture - How the CLI works internally
Best for: Understanding concepts, learning why things work the way they do, big picture
Key Features
- Dynamic Context Assembly: Merges context from various source files
- Remote Directories: Load rules from Git, HTTP, S3, and other sources
- Task-Specific Prompts: Different prompts for different tasks
- Rule-Based Context: Reusable context snippets
- Frontmatter Filtering: Select rules based on metadata
- Bootstrap Scripts: Fetch or generate context dynamically
- Parameter Substitution: Inject runtime values
- Token Estimation: Monitor context size
Supported AI Agent Formats
Automatically discovers rules from configuration files for:
- Anthropic Claude, Cursor, GitHub Copilot
- Google Gemini, OpenCode.ai, Windsurf
- Augment, Codex, and generic
.agents/directories
See Search Paths Reference for complete list.
Quick Links
- GitHub Repository - Source code and releases
- Report Issues - Bug reports and feature requests
- License - MIT License
Need Help?
- New to the CLI? Start with the Getting Started Tutorial
- Have a specific goal? Check the How-to Guides
- Looking for details? See the Reference Documentation
- Want to understand concepts? Read the Explanations