Skip to main content

Agent Task

A powerful task management platform for AI agents in Cursor AI (v0.1.0).

Overview

Agent Task is a platform that helps manage, organize, and share task-specific configurations for AI agents in Cursor. It provides a structured way to define rules, guidelines, and model context protocols (MCP) for different AI tasks.

Features

  • Task Management: Create, load, archive, and import task configurations
  • Structured Organization: Maintains a consistent directory structure for each task
  • Rule Management: Store and manage task-specific guidelines and rules
  • MCP Support: Handle Model Context Protocol servers for advanced AI configurations
  • Cross-platform: Works across different operating systems using standard paths

Installation

pip install agent-task

Directory Structure

Each task follows this standard structure:

task_name/
├── README.md           # Task documentation
├── rules/             # Task-specific guidelines
│   └── rule.mdc       # Main rules file
└── mcp/               # Model Context Protocol servers

Usage

Initialize a New Task

agent-task init task_name

List Available Tasks

agent-task list

Archive a Task

agent-task archive task_name

Import a Task

agent-task import task_name

Clone a Task from Marketplace

agent-task clone [URL]

Show Task Archive Directory

agent-task path

Configuration

The platform uses standard application directories for storing tasks and configurations:

  • App Data: User-specific application data
  • Config: User-specific configuration files
  • Cache: User-specific cache data
  • Logs: User-specific log files

Development

Project Structure

  • agent_task/
    • __init__.py - Package initialization and version
    • paths.py - Path management functionality
    • task_manager.py - Core task management logic
    • cli.py - Command-line interface implementation

Requirements

  • Python 3.6+
  • appdirs for cross-platform path management
  • pyyaml for configuration handling
  • Additional dependencies as specified in requirements.txt

License

[Add your license information here]

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Metadata

Release files for agent-task 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agent-task 0.1.3
File Size Uploaded Provenance Actions
agent_task-0.1.3.tar.gz 20.3 kB Without provenance Details for agent_task-0.1.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agent-task 0.1.3
File Interpreter ABI Platform Actions
agent_task-0.1.3-py3-none-any.whl Python 3 none any Details for agent_task-0.1.3-py3-none-any.whl

Total release size: 32.3 kB

Release files / agent_task-0.1.3.tar.gz

Download URL agent_task-0.1.3.tar.gz
Size 20.3 kB
Tags Source
SHA-256 checksum
How to use checksums
547b1c0cf0c69f0b308330dd31d36174ac45eea4b5aa3dca5102afe709799eeb
BLAKE2b-256 checksum
How to use checksums
f414c013b6febb3555991948977019752a10a4773f10021d2a0827d226ed6e57
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.0

Release files / agent_task-0.1.3-py3-none-any.whl

Download URL agent_task-0.1.3-py3-none-any.whl
Size 12.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a71a1a559ca120906edfa236b0d6045bc10ae8afa2966aa22d5ea04189d00348
BLAKE2b-256 checksum
How to use checksums
6a57efa2781b94c2bb37dbc674b7b1fffac08171430655cafd959cc78c977ab2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.10.0

Security for agent-task 0.1.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.3 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page