Automating End-to-End Pull Request Workflows with Claude Task Master An open-source command-line tool called Claude Task Master (claudetm) automates end-to-end pull request workflows by keeping Claude working until a goal is met, handling planning, coding, PR creation, CI failure fixes, review comments, and merges. Built on the Claude Agent SDK, it supports isolated OAuth and API-key profiles so multiple teams can run separate Claude subscriptions on one machine, and exposes an MCP server, REST API, and HMAC-signed webhooks for programmatic integration. The tool is MIT-licensed and installable via PyPI or Docker. Claude Task Master claudetm is a command-line tool that keeps Claude working until a goal is achieved. It plans, codes, opens pull requests, handles CI failures, addresses review comments, and merges when everything passes. The tool is built on the Claude Agent SDK and works with the Claude Code session or a direct Anthropic-compatible API. The workflow follows four stages: planning, working, PR lifecycle, and verification. In the planning stage the CLI scans the codebase, creates a task list, and defines success criteria. During working it makes changes, runs tests, commits, and pushes to a branch. The PR lifecycle stage opens a pull request, waits for CI checks, fixes failures, and responds to review comments. Finally verification runs the test suite and lint checks before declaring the task complete. Install via pip, uv, or Docker uv tool install claude-task-master Authenticate with Claude Code claude login Run a task in your project cd your-project claudetm start "Add user authentication with tests" The CLI will create a branch, push commits, open a PR, and keep the loop running until the tests pass and the PR is approved. Claude Task Master supports isolated profiles. An oauth profile stores a separate Claude Code configuration under ~/.claudetm/profiles/