neural

Implementation planning with optional adversarial cross-review (Claude Code ⇄ Codex). Tasks are sequential vertical slices, each carrying its own testable behaviors. Pass --visual to also render the plan as a self-contained HTML page (PLAN.html). Pass --skills <skills> to preload skills that shape the plan and that execute loads before coding

Execute all fixes from a REVIEW.md — address warnings, blocking issues, and gaps found during review

Test-driven execution loop — one task at a time, red→green→refactor, atomic commits

Plan vs implementation verification with goal-backward analysis and test-quality audit

Move completed features from wip to archive

Socratic interview that captures domain language, decisions, and ADRs inside .neural/wip/<feature>/

Harvest knowledge from archived features into .neural/knowledge/ — run after archiving a feature, or invoke manually to rebuild the project knowledge base

Systematic root-cause investigation for bugs and failures

Show all Neural plugin commands with descriptions and the recommended workflow

Fast-path for small tasks — mini-interview, inline plan, execute, and light review in one pass. No files generated

Show progress of all features in .neural/wip/ and suggest next steps

Sync specs (CONTEXT.md, PLAN.md, /docs) with post-implementation code