By hurblat
Automate end-to-end feature development from Linear/Jira issues using a structured workflow: create git branches, define audited requirements/specs, implement code increments with multi-agent teams, run code reviews/tests/security checks, manage PRs until approval, and update issue status.
npx claudepluginhub Hurblat/claude-constructor --plugin claude-constructorCreate pull request for increment implemented to satisfy the issue.
Create state management file for feature workflow
This command guides the implementation of new functionality using **minimal iteration cycles**. Each workflow run should implement the smallest possible increment that provides measurable value while maintaining the system's quality standards.
Check out a new git branch to be ready for implementation start.
Implement the increment using the specification in the state management file.
Generate a comprehensive summary of the completed feature implementation.
Add a comment to an issue in the configured issue tracking system.
Retrieve issue details from the configured issue tracking system for a given issue key.
Read issue from the configured issue tracking system and add the information to the state management file.
Update the status of an issue in the configured issue tracking system.
Read Claude Constructor settings and add them to the state management file.
Get user approval on requirements
Review pull request for the increment implemented to satisfy the issue.
Get user approval on implementation plan
Write E2E tests for implemented increment
Reviews implementation against specification requirements and provides APPROVED or NEEDS_CHANGES verdict
Post-implementation auditor that verifies increment-implementer agents completed their tasks correctly, thoroughly, and without cutting corners, scope creep, or unnecessary code.
Implements a specific task from a feature specification based on the agent_id assigned to it. This agent reads the specification, finds its assigned task, and implements it according to the plan.
Quality assurance specialist that validates requirements completeness, clarity, and testability before sign-off. Use after requirements definition to ensure they meet quality standards and are ready for specification writing.
This agent is called as a step in the feature implementation workflow to define requirements for a feature increment. It reads the state management file containing issue details and creates a comprehensive Requirements Definition section in a specification file. The agent focuses on capturing business value, acceptance criteria, scope boundaries, and other essential requirements without delving into implementation details.
Performs security analysis by calling the built-in /security-review command to identify vulnerabilities and security risks in the implementation
Technical specification validator that ensures implementation plans are actionable, properly parallelized, and technically sound. Use after specification writing to validate the plan is ready for implementation.
This agent is called as a step in the feature implementation workflow to create detailed implementation plans from existing requirements. It reads the state management file, analyzes the pre-defined requirements, examines the codebase, and produces a comprehensive Implementation Plan with parallelization strategy and agent assignments. The agent transforms approved requirements into actionable, parallelizable work specifications that enable multiple agents to implement features efficiently.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Uses power tools
Uses Bash, Write, or Edit tools
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification