AI Agent Ops framework for Claude Code — independent evaluator, adversarial review, and pre-commit quality gate for AI-generated code.
Command Claude Code
A multi-perspective consultation command that asks Claude, GPT, and Gemini for views on a question and analyzes how much they agree. It is intended for choices without one obvious correct answer.
Command Claude Code
An automated command that takes a natural-language coding request through design, implementation, testing, and any needed fixes. It can also stop after design or run a deeper planning process for large changes.
Command Claude Code
A combined code-quality review and design-to-implementation consistency check. It reads the changed files once, then evaluates them from both review perspectives.
Command Claude Code
A session-closing check for comparing the recorded project state with what was actually completed in Git. It separates verified work, suspected work, and items that cannot be tracked.
Command Claude Code
A command for auditing and reorganizing CLAUDE.md and AGENTS.md, files that tell coding agents how a project should be worked on. It separates general instructions from detailed procedures, path-specific rules, safeguards, and current state.
Command Claude Code
A deep planning command that explores options, reviews them, and refines the result through several stages. It produces a detailed plan document with risks, unknowns, and verification checks.
Command Claude Code
A command that turns an existing plan into a detailed technical design for building the feature.
Command Claude Code
A migration command that converts older NOVA-STATE.md project-state files into the current v3 work-item registry, a structured record of tasks and their status. It supports checking and previewing the conversion before applying it.
Command Claude Code
A project-status diagnosis and next-step recommendation command for the Nova workflow. It reads the project state, recent Git history, and planning, design, and verification documents.
Command Claude Code
A command that turns a feature request into a structured planning document using the Context–Problem–Solution framework.
Command Claude Code
An adversarial code review that assumes hidden bugs may exist and checks changes for correctness, structure, and security concerns.
Command Claude Code
A full development cycle that carries out an implementation and then verifies the result, with an option to verify existing work only.
Command Claude Code
A codebase onboarding briefing that examines a new project's files, tools, main entry points, and marked technical debt.
Command Claude Code
A project setup and upgrade helper for Nova Quality Gate, a set of checks and working rules for reviewing and verifying code changes.
Command Claude Code
A command that generates a standalone HTML dashboard showing project phases, sprints, group progress, and roadmap drift.
Command Claude Code
A command that evaluates a website's user interface and user experience from its code and, optionally, its running screens.
Command Claude Code
A worktree setup command that reconnects environment files, secrets, and configuration from the main Git repository to a separate worktree. A worktree is another working directory linked to the same repository.
Command
A command that performs a static security review of a Nova plug-in’s files, without running the code. It checks the plug-in manifest, shell hooks, agent definitions, skills, and commands against security rules.
Command
A command that scans technology trends and can propose or implement improvements to Nova, an AI system. It supports scan-only, approved application, automatic workflows, source selection, GitHub popularity thresholds, and recording user decisions.