Automating Claude-Based Development with Claude Task Master A developer built Claude Task Master (CLI `claudetm`), an open tool on the Claude Agent SDK that autonomously runs the full pull-request lifecycle: it reads a high-level goal, writes a plan with success criteria, makes code changes, opens PRs, monitors CI, resolves review comments, and merges when criteria are met. The tool persists state so interrupted runs resume where they left off, supports isolated profiles for multiple Claude subscriptions, and lets concurrent instances coordinate through a mailbox system over REST, MCP, or CLI. It also exposes REST, MCP, and webhook integrations for embedding in CI/CD pipelines and automation platforms. Developers using Claude Code often spend time managing pull requests, fixing CI failures, and handling review comments. Claude Task Master CLI claudetm removes that manual overhead by orchestrating the entire development loop autonomously. The tool reads a high-level goal, creates a detailed plan, executes code changes, opens pull requests, monitors CI, addresses feedback, and merges when the defined success criteria are satisfied. This article explains how the system works, its core features, and how to integrate it into existing workflows. Claude Task Master is built on the Claude Agent SDK and follows a PR-based workflow. The main concepts are: The typical workflow proceeds through four phases: claudetm reads the codebase, creates a task list organized by pull requests, and writes a plan file. The plan includes the goal, the tasks, and the criteria that define success. Each phase can be interrupted at any point. Because the state is persisted, a subsequent run of claudetm picks up where it left off, re-establishes the PR, and continues the verification. Claude Task Master supports profiles to isolate credentials and configuration for multiple Claude subscriptions. A profile is a directory under ~/.claudetm/profiles/