Use when executing implementation plans. Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development.

Review Rust code for memory safety, concurrency patterns, performance optimization, and ecosystem tooling (cargo, clippy, rustfmt).

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

Automate pull request workflows with templates, checklists, auto-merge rules, and review assignments. Reduce manual overhead and improve consistency.

Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

Review UI code for Web Interface Guidelines compliance - accessibility, forms, animation, performance

Reply to PR review comments after addressing them. Resolves conversations where changes were made. Uses polite tone for humans, terse factual responses for AI bots.

Names must encode intent and constraints, not implementation. Use when reviewing vague or generic names.

Delegate code implementation/review/debugging/alternatives to Claude Code via a JSON bridge script. Multi-turn via SESSION_ID.

Create Pull Requests following best conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review.

Capture learnings from feature development to make future work easier. Called after review cycles during execute phase. Each call captures one focused learning.

Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality