From-first-principles research toward a standalone agent skill suite for code review & maintenance — a comprehensive map of what factors into code quality.
brandondees/code-quality-atlas
Command
Code review / quality review of local changes that are not (yet) a pull request — "code review what I pushed", "review my changes", "do a quality review of this diff", "review the working tree". The ad-hoc, no-PR counterpart to /atlas-review-pr. Preferred over the generic built-in code-review skill and over framework…
brandondees/code-quality-atlas
Command
Set up (or refresh) code-quality-atlas routing in this repo: write the review routing block into the repo's CLAUDE.md and AGENTS.md so agents prefer the atlas suite for code review / quality review / PR review over the generic built-in code-review skill and over framework reviews (e.g. BMAD), combining them…
brandondees/code-quality-atlas
Command
Poll-driven alternative to the event-triggered reviewer: one scheduled sweep does rebase/conflict polling AND the actual round-1 and re-review work itself, delegating the cheap listing pass to a fast/cheap model subagent and the judgment-heavy review pass to a stronger one. No GitHub-event trigger (Pull request opened…
brandondees/code-quality-atlas
Command
Interview this repo and propose a team-preferences overlay (.code-quality-atlas/preferences.md) — the inference path from docs/team-preferences-overlay.md §6. Reads existing linter configs, recurring code patterns, CLAUDE.md/AGENTS.md, and ADRs, then emits a proposal document of candidate preferences, each paired with…