
Generate a session-end summary that passes the stop hook on the first attempt
Use when about to start TDD on a new feature or bugfix, before writing the first test — adds a design thinking phase that produces a test plan
Run code review with findings-first, severity-ordered output focused on bugs, regressions, edge cases, error handling, performance, architecture, caller impact, and missing tests.
Pre-execution self-check to validate a plan before writing any code
7-phase development workflow for declarative task execution across Claude.ai and Claude Code sessions
Plan implementation work before coding by defining public interfaces, real collaborator boundaries, and vertical RED or VERIFY slices.
Review an implementation plan before execution to catch missed success criteria, scope creep, constraint violations, unverified assumptions, and missed reuse opportunities.
Retrospective entry format for capturing lessons learned at task close-out
Session-persistent task management using docs/tasks/ files for continuity across Claude Code sessions
Manage task files in docs/tasks/open and docs/tasks/closed, including task discovery, resume/create rules, append-only Attempts logging, Left Off At updates, Code Review field handling, and needs verification closeout.
Follow the end-to-end delivery workflow for planning, task-file management, execution, code review, verification, and closeout without relying on Claude-specific hooks or command conventions.