agentize

Review code changes via agent with isolated context and Opus model

Review code changes from current HEAD to main/HEAD following review standards

Create a git commit with meaningful commit messages following project standards

Orchestrate the complete implementation workflow from a GitHub issue with an implementation plan to a fully implemented feature.

**IMPORTANT**: Keep a correct mindset when this command is invoked.

Create GitHub [plan] issues from user-provided existing implementation plan from plan mode or etc.

Review code changes and optionally create a pull request with --open flag

Fetch unresolved PR review threads and apply fixes with user confirmation

Set up a GitHub Projects v2 board with agentize-compatible Status fields, labels, and automation workflows

This command is an alias for `/mega-planner`. Execute the mega-planner command with the provided arguments.

Synchronize local main/master branch with upstream (or origin) using rebase

Multi-perspective code review with inter-reviewer discussion using agent teams

**IMPORTANT**: Keep a correct mindset when this command is invoked.

This directory contains specialized agents for the agentize plugin.

Research SOTA solutions and propose innovative, bold approaches for implementation planning

Comprehensive code review with enhanced quality standards using Opus for long context analysis

Research SOTA solutions and propose innovative approaches with code diff drafts

Reduce total code footprint - allows large changes but limits unreasonable code growth

Destructive refactoring proposer - deletes aggressively, rewrites for simplicity, provides code diff drafts

Validate assumptions and analyze technical feasibility of BOTH proposals (bold + paranoia)

Simplify BOTH proposals (bold + paranoia) following "less is more" philosophy

Lightweight single-agent planner for simple modifications (<5 files, <150 LOC, repo-only knowledge)

Validate assumptions and analyze technical feasibility of implementation proposals

Simplify proposals following "less is more" philosophy to minimize complexity

Gather codebase context and constraints before multi-agent debate begins

Commit the staged changes to git with meaningful messages.

How to debug a codebase when a test case fails to pass. If you cannot figure it out, how to report the bug through a Github Issue.

Generate comprehensive documentation checklist for feature implementation

Instructs AI agents on documentation standards for design docs, folder READMEs, source code interfaces, and test cases

Synthesize consensus implementation plan from multi-agent debate reports using external AI review

Synthesize implementation plan(s) from 5-agent debate using external AI - exposes disagreements as developer decisions

Create a development branch for a given GitHub issue with standardized naming

Drive implementation forward incrementally with automatic progress tracking, LOC monitoring, and milestone checkpoint creation

Move or rename a file while automatically updating all references in source code and documentation

Create GitHub issues from conversation context with proper formatting and tag selection

Create GitHub pull requests from conversation context with proper formatting and tag selection

Create comprehensive implementation plans with detailed file-level changes and test strategies

Systematic code review skill checking documentation quality and promoting code reuse

Skill for reviewing shell scripts with shell-neutral behavior with best efforts.

9 hooks across 8 events