plan-build-run

Run multiple phases hands-free. Chains discuss, plan, build, and verify automatically.

Start a new project. Deep questioning, research, requirements, and roadmap.

Execute all plans in a phase. Spawns agents to build in parallel, commits atomically.

Configure settings: depth, model profiles, features, git, and gates.

Execute the next logical step automatically. No prompts, no decisions — just do it.

Systematic debugging with hypothesis testing. Persistent across sessions.

Explore ideas, think through approaches, and route insights to the right artifacts.

Check planning directory integrity. Find and fix corrupted state.

Command reference and workflow guide for Plan-Build-Run.

Import external plans. Validates context, detects conflicts, generates PLAN.md.

Refresh or query codebase intelligence (file graph, APIs, dependencies, architecture).

Manage milestones: new, complete, audit, gaps.

Zero-friction idea capture. Append, list, or promote notes to todos.

Save your current session state for later resumption.

Create a detailed plan for a phase. Research, plan, and verify before building.

Analyze Claude Code session history to generate a developer behavioral profile across 8 dimensions.

Execute an ad-hoc task with atomic commits. Skips full plan/review.

Pick up where you left off. Restores context and suggests next action.

Verify the build matched the plan. Automated checks + walkthrough with you.

Analyze an existing codebase. Maps structure, architecture, conventions, and concerns.

Display project statistics — phases, plans, requirements, git metrics, and timeline.

Show current project status and suggest what to do next.

Generate tests for completed phase code. Detects test framework and targets key files.

File-based persistent todos. Add, list, complete — survives sessions.

Generate UI-SPEC.md design contracts for frontend-heavy phases.

Retroactive visual audit of UI implementation with 1-4 scoring per dimension.

Reconfigure an existing Plan-Build-Run project (models, features, CLAUDE.md).

Talk through a phase before planning. Identifies gray areas and captures your decisions.

Post-build quality gate. Identifies test gaps and spawns nyquist-auditor to fill them.

Generate comprehensive milestone summary from archived artifacts. For team onboarding and stakeholder review.

Manage backlog items — ideas not ready for active planning. Add, review, promote, or remove.

Plant forward-looking ideas with trigger conditions that auto-surface at the right milestone.

Persistent context threads for cross-session work that spans phases. Lighter than pause/resume.

Post-mortem investigation for failed or stuck workflows. Analyzes git history and planning artifacts.

Surface Claude's assumptions about a phase before planning begins.

Execute a trivial task inline without subagent overhead. No planning, no research — just do it and commit.

Review past Claude Code sessions for PBR workflow compliance and UX quality.

Generate post-session summary with work performed, outcomes, and resource usage.

Switch the active model profile. Presets: quality, balanced, budget, adaptive. Supports custom profiles from config.json model_profiles.

Create a rich PR from planning artifacts (SUMMARY one-liners, requirement coverage, verification status).