Metadata-Version: 2.4
Name: agentry-cli
Version: 0.1.0
Summary: A CLI tool to easily reuse AI agent instructions, skills, philosophies or other prompt files.
Project-URL: Homepage, https://agent-wisdom.gitlab.io/agentry/
Project-URL: Repository, https://gitlab.com/agent-wisdom/agentry
Project-URL: Documentation, https://agent-wisdom.gitlab.io/agentry/
Project-URL: Bug Tracker, https://gitlab.com/agent-wisdom/agentry/-/issues
Project-URL: Changelog, https://gitlab.com/agent-wisdom/agentry/-/blob/main/CHANGELOG.md
Author-email: Zurab Mujirishvili <zurab.mu@gmail.com>
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Typing :: Typed
Requires-Python: >=3.13
Requires-Dist: anyio>=4.13.0
Requires-Dist: httpx>=0.28.1
Requires-Dist: pydantic>=2.13.4
Requires-Dist: rich>=15.0.0
Requires-Dist: typer>=0.25.1
Description-Content-Type: text/markdown

# Agentry

A CLI tool to easily reuse AI agent instructions, skills, philosophies or other prompt files.

## Installation

Python 3.13+ is required.

```bash
pip install agentry
```

Or with [uv](https://docs.astral.sh/uv/):

```bash
uv tool install agentry
```

## Quick Start

```bash
agentry install https://gitlab.com/owner/repo/-/tree/main/commands "**/*.md" \
  --integration claude --scope user
```

Run without arguments to answer prompts interactively:

```bash
agentry install
```

## Usage

Run `agentry --help` to see all available options.

| Argument / Option | Short | Description                                                                 |
| ----------------- | ----- | --------------------------------------------------------------------------- |
| `REPO`            |       | Source URL or local path                                                    |
| `PATTERN`         |       | Glob pattern for files to install, e.g. `**/*.md`                           |
| `--integration`   | `-i`  | Target integration — currently `claude`                                     |
| `--scope`         | `-s`  | `user` or `project`                                                         |
| `--token`         | `-t`  | Auth token for private repositories (or `AGENTRY_TOKEN` env var)            |

### Scopes

| Scope     | Effect                                 |
| --------- | -------------------------------------- |
| `user`    | Prompts available across all projects |
| `project` | Prompts scoped to the current project |


### Remote URL format

GitLab tree URLs are currently supported:

```
https://gitlab.com/{owner}/{repo}/-/tree/{branch}[/{subpath}]
```

Point to a branch root or a subdirectory. Only files matching `PATTERN` within that tree are installed.

```bash
# Entire repo, main branch
agentry install https://gitlab.com/org/prompts/-/tree/main "**/*.md" --scope user

# Subdirectory on a different branch
agentry install https://gitlab.com/org/prompts/-/tree/develop/commands "*.md" --scope project
```

### Private repositories

```bash
# Pass inline
agentry install https://gitlab.com/org/private-prompts/-/tree/main "**/*.md" --token glpat-xxxx

# Or via environment variable
export AGENTRY_TOKEN=glpat-xxxx
agentry install https://gitlab.com/org/private-prompts/-/tree/main "**/*.md"
```

### Local paths

```bash
agentry install ./my-prompts "*.md" --integration claude --scope project
```

## Development

### Prerequisites

- Python >= 3.13
- [uv](https://docs.astral.sh/uv/) (recommended)
- [just](https://github.com/casey/just) (optional)

### Getting Started

```bash
git clone https://gitlab.com/agent-wisdom/agentry.git
cd agentry
uv sync
uv run pre-commit install
```

### Running Checks

```bash
just check
# or
uv run ruff check --fix && uv run ruff format && uv run pyright && uv run pytest
```

## License

MIT — see [LICENSE](LICENSE).
