Distribute artifacts
Now that Packmind contains coding standards and recipes, let's distribute them to your Git Repositories.
The distribution will commit instructions files that will be used by AI Agents (Claude Code, Cursor, etc.).
Supported AI Agents
Packmind supports multiple AI coding assistants. Organization administrators can choose which agents to enable in Settings → Distribution → Rendering. See Manage AI Agent Rendering for details.
Here is an overview of the supported agents:
| AI Agent | What It Does | File Location |
|---|---|---|
| Packmind | Internal renderer (required) | .packmind/ |
| AGENTS.md | Updates instructions file | AGENTS.md |
| GitHub Copilot | Updates instructions file | .github/copilot-instructions.md |
| Cursor | Creates rules in YAML format | .cursor/rules/ |
| Claude Code | Updates instructions file | CLAUDE.md |
| Junie | Updates guidelines file | .junie/guidelines.md |
| Gitlab Duo | Updates chat rules file | .gitlab/duo/chat-rules.md |
| Continue | Creates rules in Markdown format | .continue/rules/packmind/ |
When you distribute standards or recipes, only the enabled agents will receive updates. The Packmind renderer is always active and creates files in the .packmind/ directory that are used by other agents.
You can create an issue in our repository to request support for additional AI coding assistants
How to Distribute
There are three ways to distribute packages to your repositories:
- Using the Packmind app - Distribute packages through the web interface with full control over targets and repositories
- Using packmind-cli - Install packages directly from your terminal, useful for CI/CD pipelines and local development
- Using the MCP tool - Install packages directly from AI agents that support MCP (Model Context Protocol)
Distribution Methods Overview
| Method | Best For | Git Provider Management |
|---|---|---|
| App | Centralized distribution, team coordination | Full control via connected Git providers |
| CLI | CI/CD pipelines, local development | Creates read-only provider entries |
| MCP | AI-assisted development, agent workflows | Creates read-only provider entries |
Distribute via the App
To distribute standards and recipes, you need to add them to a package.
A package is a curated collection of recipes and standards grouped together (e.g., "Frontend React Standards", "Backend API Guidelines"). When you distribute a package:
- All recipes and standards in the package are distributed together
- The latest version of each item is used
- A single commit contains all the package content
- You can distribute multiple packages at once to the same target
To distribute packages:
- Navigate to the Packages section
- Select the package(s) you want to distribute
- Click Distribute and choose your target repositories
- Confirm the Distribution
This approach is useful when you want to:
- Distribute related guidelines together
- Maintain consistent sets of standards across projects
- Organize guidelines by technology, team, or project structure
For more information on creating and managing packages, see Packages Management.
Distribute via packmind-cli
You can also distribute packages directly from your terminal using the packmind-cli command:
packmind-cli install <package-slug>
For example:
packmind-cli install backend-standards frontend-react
This will:
- Fetch the specified packages from Packmind
- Generate the instruction files for all enabled AI agents
- Write the files to your local repository
- Notify Packmind that a distribution occurred
CLI Distribution Considerations
When you distribute packages using the CLI, Packmind automatically creates a Git provider entry to track the distribution. However, these CLI-created providers have some limitations:
Git providers created through CLI distributions do not have an associated token. This means:
- You cannot trigger new distributions from the app for these repositories
- You cannot add new targets to these providers from the app
- The provider appears in your organization's Git settings but with limited functionality
To enable full management from the app, connect a Git provider with a valid token in Settings → Git Providers.
When to Use CLI Distribution
The CLI approach is ideal for:
- CI/CD pipelines - Automate distribution as part of your deployment process
- Local development - Quickly install packages without leaving your terminal
- Monorepos - Use
packmind-cli install --recursiveto install packages for allpackmind.jsonfiles in the repository - Self-hosted Git instances - Distribute to repositories that aren't connected to the app
Distribute via MCP Tool
If you're using an AI agent that supports MCP (Model Context Protocol) and have the Packmind MCP server configured, you can install packages directly through your AI assistant using the install_package tool.
How It Works
The MCP tool provides a two-step installation process:
- Get installation instructions - Call
install_packagewith your package slugs to receive the list of file updates needed - Apply the changes - The AI agent applies the file updates to your repository
Usage
Ask your AI assistant to install Packmind packages. For example:
"Install the backend-standards package from Packmind"
The AI agent will:
- Call the
install_packageMCP tool with the specified package slugs - Receive the file contents for all enabled AI agent renderers
- Write or update the instruction files in your repository
- Notify Packmind that a distribution occurred
MCP Distribution Considerations
Similar to CLI distributions, MCP-based distributions create Git provider entries with limited functionality:
Git providers created through MCP distributions do not have an associated token. This means:
- You cannot trigger new distributions from the app for these repositories
- You cannot add new targets to these providers from the app
- The provider appears in your organization's Git settings but with limited functionality
To enable full management from the app, connect a Git provider with a valid token in Settings → Git Providers.
When to Use MCP Distribution
The MCP approach is ideal for:
- AI-assisted development - Let your AI coding assistant manage package installation as part of your workflow
- Interactive setup - Get guidance and validation from your AI agent during installation
- Quick iterations - Update packages without switching context from your AI chat interface
- Onboarding new projects - Have your AI assistant set up Packmind standards in new repositories
Removing Packages
When you no longer need a package in your repository, you can remove it using either the app or the CLI.
Remove via the App
In the Packmind app, you can remove packages one-by-one from your distributions:
- Navigate to the Packages section
- Open the package you want to remove
- Click Remove from target and confirm the removal
Remove via the CLI
There are two ways to remove packages using the CLI:
Option 1: Use the remove command
packmind-cli remove <package-slug>
For example:
packmind-cli remove backend-standards
Option 2: Edit packmind.json and reinstall
- Open your
packmind.jsonfile - Remove the package slug from the packages list
- Run the install command to update your repository:
packmind-cli install
This approach is useful when you want to make multiple changes to your package configuration at once.