agentic-toolbelt 0.1.16

Packages agent payload assets and installs them into a project via the agentic-set CLI.

Agentic Toolbelt

Author: Roberto Del Prete

Purpose

agentic-toolbelt packages reproducible agent-operating defaults and installs them into any project with a CLI. pip install only installs the Python package and its bundled resources into the environment. To copy .agents, .codex, and AGENTS.md into a target project, run agentic-set in that project directory.

The installer payload includes:

• .agents
• .codex
• AGENTS.md

The repository exists to standardize how autonomous agents are configured, launched, and governed across different codebases.

Features

• CLI entrypoints:
  • agentic-set: installs the packaged AGENTS.md prompt
• Copies packaged payload directly into the directory where the command is launched
• Supports --force to overwrite existing .agents, .codex, and AGENTS.md
• Safe copy flow with temporary staging and cleanup

Installation

agentic-toolbelt supports Python 3.9 and newer on any platform with a supported Python interpreter.

From the repository root:

python -m pip install .

Then bootstrap the current project:

agentic-set

For local development and test runs:

python -m pip install -e ".[test]"

This registers the agentic-set console script in that environment. It does not copy payload files into your repository until you run the command.

Usage

From any project directory, install the default baseline:

agentic-set

Force overwrite when files already exist:

agentic-set --force

Docs Site

A graphical overview page is available at:

• docs/index.html

Open it in a browser to view the repo concept, architecture, and CLI workflows.

Development

• Python package entrypoint is also declared in setup.py and pyproject.toml.
• Current package version is maintained in both pyproject.toml and setup.py.

Release Checks

Build and verify the distributable artifacts from the repository root:

python -m pytest
python -m build
python -m twine check dist/*

If you want a smoke test of the built wheel, install it into a clean virtual environment and run:

agentic-set --help