blakesims

Use when operating as the Pi architecture/design governor for the stores substrate, or when asking Pi for design review, priority coherence, contract ratification advice, or architectural approval over agent-comm.

Use when operating as the Claude Code engine controller for the stores substrate: driving tasks, daemon/worktrees, codex/rebase loops, and multi-agent coordination.

Use for the temporary front-of-engine queue-curation role in stores: triages observations/intake/tasks, deduplicates stale/noisy rows, drafts priority recommendations, and delegates backlog analysis to subagents without implementing code.

Use during wind-down when acting as engine-controller and preparing the next engine-controller agent handover.

Use for the session-scoped read-only codex sensor role in stores: watches in_review tasks, rebases review worktrees, runs codex, and posts structured review digests over agent-comm without writing substrate state or code.

Use during wind-down when acting as reviewer-runner and handing off codex/review state to the next reviewer-runner.

Use during wind-down when acting as Pi architect and handing off architectural state, priorities, and pending decisions.

Use when Blake says context is high, asks to wind down, pause/clear the engine, prepare handover, or end a multi-agent stores session cleanly. Coordinates substrate-agent/reviewer-runner feedback, updates SOP skills/docs, and produces next-session handover…

Execute a phase of an implementation plan. Follow tasks exactly, write code, run tests. Use when asked to execute, implement, or work on a specific phase.

Create implementation plans for tasks. Use when asked to plan, create a plan, or start a new task. Outputs to main.md in the task directory.

Adversarial code review of executed phases. Verify implementation matches plan, find bugs and edge cases. Use after phase execution.

Mini review before next phase. Incorporate learnings, verify phase is ready, update plan if needed. Use between phases to ensure continuity.

Review implementation plans. Validate open questions, find gaps, assess readiness. Use when asked to review a plan or after planning completes.

Start the autonomous multi-agent development workflow. Use when the user explicitly wants task-workflow to run the core development cycle end-to-end.

Understand the multi-agent task workflow structure. Reference this when working on tasks in a tasks/ directory. Defines main.md format and agent responsibilities.

Guided PRD creation. Loads kit template, asks customisation questions, generates PRD and mockup at project root.

Import an existing project into the CCA workflow. Detects what you already have (PRD, code, tasks) and sets up the missing pieces so you can start building.

Welcome and onboard a new student. Set up their project with the CCA workflow, explain what's happening at every step, and guide them to their first kit.

Build your project. Orchestrates the full workflow: creates a task from your PRD, plans the implementation, then builds it phase by phase with quality checks.

Browse and download starter kits. Each kit provides a PRD template and customisation points for a specific project type.