Setup Coding Quality Checks

Set up a local correctness environment where AI agents can work safely. Keep scope tight: formatter, linter, typecheck, tests, security scanners when warranted, git hooks, and existing build checks only. Do not turn this into a broad validation framework.

Principles

• Use Coding Quality Checks as the umbrella term.
• Explore before asking. If repo evidence answers a question, use it.
• Ask one decision at a time, with a recommended answer.
• Prefer strict correctness over convenience; brownfield repos may fail immediately.
• Do not auto-format or lint-autofix source without separate confirmation.
• Do not invent build steps or aggregate commands. Preserve repo terminology.
• Sub-agents may discover and draft plans; the main agent owns decisions, confirmation, and edits.

1. Discover

Inspect before asking. Use sub-agents freely when useful; give each a radically different angle: stack discovery, existing tooling, security/hook risks, or greenfield planning clues.

Look for repo instructions (AGENTS.md, .cursor/rules, copilot instructions), Sandcastle docs (.sandcastle/**/*.md), package manifests, lockfiles, existing configs/scripts, tests, source layout, and existing CI files. Use CI as evidence, but ask before editing it.