Task Agent

Task Agent is a small, forkable workspace for task-first autonomous-agent workflows.

It is intentionally generic: no private task history, no local data, and no bundled personal integrations. Project-level operating rules live in AGENTS.md.

What Is Included

• tasks/ skeleton for durable task artifacts
• data/projects/ skeleton for multi-task project records
• skills/task-creator/ for creating task directories and updating the index
• skills/task-runner/ for parent-child CLI agent execution and optional Codex multi-agent workflows
• skills/project-organizer/ for durable project records
• skills/repo-health/ for restore and publication checks
• skills/skill-maintainer/ for creating or changing skills
• docs/ for architecture, task execution, and self-development workflows

Quick Start

Create a virtual environment and install test dependencies:

python3 -m venv .venv
.venv/bin/pip install -r requirements.lock

Create a task:

skills/task-creator/scripts/create_task.sh "Example task" "Try the task-agent workflow"

Run health checks:

.venv/bin/python skills/repo-health/scripts/check_repo_health.py --allow-empty-tasks
PYTHONPATH=skills/task-runner/scripts .venv/bin/python -m pytest skills/task-runner/tests

Multi-Agent Workflow

skills/task-runner/scripts/task_runner.py supports --workflow multi-agent-dev for explicit team-of-agents development runs via Codex CLI.

The workflow uses role prompts from /opt/projects/agents by default. If that checkout is missing, it clones https://github.com/rdudov/agents.git before startup and verifies the required prompt files. Override with:

• --agents-dir
• --agents-repo-url
• CODEX_MULTI_AGENT_PROMPTS_REPO

Documentation

• docs/architecture.md
• docs/task-execution.md
• docs/self-development.md

License

Task Agent is released under the MIT License.

Local State

tasks/ and data/ are durable local artifacts. This template tracks only skeleton files; real task history and reusable data should be backed up by your own local backup flow.