documenting-decisions
>
implementing-plans
Disciplined plan execution with checkpoint validation, progress tracking, and verification at each step. Follows an approved plan strictly, running verification criteria before proceeding.
researching-codebase
Thorough codebase exploration that builds understanding through collaborative dialogue. Investigates architecture, patterns, and implementation details before planning or making changes.
writing-plans
Transform research findings into actionable implementation plans with granular steps, verification criteria, and stakes-based enforcement. Plans serve as contracts between human and AI.
systematic-debugging
>
verification-before-completion
>
brainstorming
>
parallel-agents
>
receiving-code-review
>
security-review
>
finishing-work
>
git-worktrees
>
reviewing-code
>
research-plan-implement
End-to-end Research-Plan-Implement pipeline using parallel subagents. Each phase (research, plan, implement) runs in its own context window with file artifacts as the communication channel between phases.
synthesizing-research
Consolidate multiple parallel research documents into a single unified report. Produces a self-contained document that a reader with no prior context can understand completely.
test-driven-development
>