No. It is a scaffold that prepares a project for coding agents and local-first model routing.

No. The wizard, hardware probe, credential templates, adapter generation, and select-model recommendations work without calling a model. You need an LLM only when a coding tool such as OpenCode or OpenClaude starts an actual agent session.

Yes, when it is running interactively and the selected coding environment is missing. It asks before installing. You can also run coding-scaffold setup-tool --tool opencode to validate the tool, or add --install to install a missing tool intentionally.

Yes. Use coding-scaffold setup-addon --addon llmfit, routellm, open-multi-agent, or obsidian. The wizard can also offer add-ons interactively. RouteLLM installs into the active Python environment, Open Multi-Agent installs into the target Node.js project, and Obsidian remains manual on WSL because it is a desktop app.

No. It can work local-only. Cloud providers are used only when credentials are configured and the project privacy mode allows it.

No. It writes ignored templates such as .coding-scaffold/.env.local, but it does not commit, print, or collect secret values.

Copilot is useful for completion and chat. CodingScaffold focuses on agentic workflows: inspect, plan, edit, verify, review, and preserve reusable team habits.

Markdown works in Git, GitHub, GitLab, editors, Obsidian, and memory tools. It is easy to review and easy to migrate.

No. Start with the wizard, OpenCode, skills, and knowledge. Add RouteLLM or Open Multi-Agent only after the team has a proven need.