Skip to main content

Shared Claude Code workflow for Quber projects (Jira + GitHub automation)

Project description

Quber Workflow

Shared Claude Code workflow for Quber projects (Jira + GitHub automation).

PyPI Python License

Overview

quber-workflow provides a standardized Claude Code workflow across all Quber projects, including:

  • Jira Workflow Agent - Automated Jira issue management
  • GitHub Workflow Agent - Automated PR and branch workflows
  • Skills - Bash scripts for Jira and GitHub operations
  • GitHub Actions - Automated Jira status transitions
  • Documentation - Workflow specs and PR evidence guidelines

Features

  •  Deny-by-default permissions - Enforces proper agent delegation
  •  Git worktree workflow - Prevents branch pollution
  •  Jira automation - Status transitions on branch/PR events
  •  PR evidence requirements - Embedded quality standards
  •  Context-efficient - 95%+ reduction vs MCP servers

Installation

# Using pip
pip install quber-workflow

# Using uv (recommended)
uv pip install quber-workflow

Usage

Initialize New Project

# Navigate to your project directory
cd my-quber-project

# Initialize workflow
quber-workflow init \
  --project=my-project \
  --package=my_project \
  --repo=username/my-project \
  --jira-key=QUE

This creates:

  • .claude/agents/ - jira-workflow and github-workflow agents
  • .claude/skills/ - jira-operations and github-operations skills
  • .claude/settings.json - deny-based permissions
  • .github/workflows/jira-transition.yml - Jira automation
  • docs/ - workflow specifications and guidelines

Update Existing Project

# Update workflow files to latest version
quber-workflow update

Migrate Existing Project

# Migrate with automatic backup
quber-workflow migrate

Environment Variables

Set these for Jira and GitHub operations:

# GitHub (for gh CLI)
export GH_TOKEN="ghp_..."
# or
export GITHUB_PERSONAL_ACCESS_TOKEN="ghp_..."

# Jira (for REST API)
export ATLASSIAN_SITE_NAME="yoursite.atlassian.net"
export ATLASSIAN_USER_EMAIL="your.email@example.com"
export ATLASSIAN_API_TOKEN="your-api-token"

GitHub Secrets

Configure these secrets for GitHub Actions:

  • JIRA_BASE_URL - Your Jira site URL
  • JIRA_USER_EMAIL - Jira account email
  • JIRA_API_TOKEN - Jira API token

Architecture

Agent-Based Workflow

Main Claude Agent (quber-analyst)
    \x00> jira-workflow agent (via Task tool)
       \x00> jira-operations skill (bash scripts)
           \x00> Jira REST API
    \x00> github-workflow agent (via Task tool)
        \x00> github-operations skill (bash scripts)
            \x00> gh CLI / GitHub API

Why This Approach?

  • Minimal context overhead - ~100 tokens vs 46k with MCP servers
  • On-demand loading - Skills load only when agents are invoked
  • No external dependencies - Just bash, curl, jq, and gh CLI
  • Easy debugging - Scripts are visible and testable
  • Full control - Auditable code in your repository

Documentation

Development

Setup

# Clone repository
git clone https://github.com/xmandeng/quber-workflow.git
cd quber-workflow

# Install dependencies
uv sync

# Run tests
uv run pytest

# Type checking
uv run mypy src/

# Linting
uv run ruff check src/

Build and Publish

# Build package
uv build

# Publish to Test PyPI
uv publish \
  --publish-url https://test.pypi.org/legacy/ \
  --username __token__ \
  --password $TEST_PYPI_TOKEN

# Publish to Production PyPI
uv publish --username __token__ --password $PYPI_TOKEN

Requirements

  • Python >= 3.9
  • gh CLI (for GitHub operations)
  • jq (for JSON parsing)
  • curl (for Jira REST API)

Contributing

Contributions welcome! Please:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Related Projects

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

quber_workflow-0.1.1.tar.gz (44.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

quber_workflow-0.1.1-py3-none-any.whl (64.3 kB view details)

Uploaded Python 3

File details

Details for the file quber_workflow-0.1.1.tar.gz.

File metadata

  • Download URL: quber_workflow-0.1.1.tar.gz
  • Upload date:
  • Size: 44.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.11

File hashes

Hashes for quber_workflow-0.1.1.tar.gz
Algorithm Hash digest
SHA256 0b8c8a0e83ea3d51b2b0379b79c9de561e7e6d8eb73c11ff37fa058fc7d7a958
MD5 4a8e52ca3b229d3efd6099280ae09953
BLAKE2b-256 b8d87f8f560d04754644dbb7b30a0f7c7693e69d900186cc74084c47bef64835

See more details on using hashes here.

File details

Details for the file quber_workflow-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for quber_workflow-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a17cd7bf3505c64567a7e711328ca5ceff6b617e7d2eb97650df6ae30da70fa0
MD5 28b5eb77fee29b094b0c8ac022a0b9cc
BLAKE2b-256 3cdc46dc1885fe0ba2c6d6857ac3475a0be3bbb5628ad26a955425a385646165

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page