Commands and agents from humanlayer, but without the thought syncing
/plugin marketplace add jeffh/claude-plugins
/plugin install humanlayer@jeffh/claude-plugins
Create git commits for session changes with clear, atomic messages
Generate comprehensive PR descriptions following repository templates
Create git commits with user approval and no Claude attribution
Create handoff document for transferring work to another session
Create detailed implementation plans through interactive research and iteration
Create detailed implementation plans with thorough research and iteration
Create implementation plans with thorough research (no thoughts directory)
Create worktree and launch implementation session for a plan
Debug issues by investigating logs, database state, and git history
Create Linear ticket and PR for experimental features after implementation
Implement technical plans from thoughts/shared/plans with verification
Iterate on existing implementation plans with thorough research and updates
Manage Linear tickets - create, update, comment, and follow workflow patterns
Set up worktree for reviewing colleague's branch
Research ticket and launch planning session
Execute ralph plan and implementation for a ticket
Implement highest priority small Linear ticket with worktree setup
Create implementation plan for highest priority Linear ticket ready for spec
Research highest priority Linear ticket needing investigation
Document codebase as-is with thoughts directory for historical context
Research codebase comprehensively using parallel sub-agents
Document codebase as-is without evaluation or recommendations
Resume work from handoff document with context analysis and validation
Validate implementation against plan, verify success criteria, identify issues
Automated code review for pull requests using multiple specialized agents with confidence-based scoring
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification