Scan and document post-merge state

Run post-merge checks on recent main merges, update tracking docs, flag refactors for escalation.

Prompt
→ Claude Code
/loop 1d Run post-merge-scan on merges to main (last 7d). Update post-merge-state.md. Small doc/link fixes only in worktree. Escalate refactors
claude-code

Source: rajveersingh11 ↗graded C · 65/100 — how grades work (Safety Score v2) →

/scheduleQualitymedium risknew

Keep post-merge cleanup in sync

Run post-merge scans on recent main merges, update docs, and propose minor fixes—escalate architectural changes.

prompt
→ Claude Code
/loop 1d Run post-merge-scan on merges to main in the last 48h. Update post-merge-state.md. Propose only small doc/lint/comment fixes in a worktree. Ticket anything architectural. Human gate on denylist paths
/goalQualitylow risknew

Fix all ESLint errors

Resolve every ESLint violation in the gen-ai frontend until linting passes cleanly.

prompt
→ Claude Code
/goal all ESLint errors in packages/gen-ai/frontend/src are resolved and pnpm run lint --filter=@odh-dashboard/gen-ai exits 0
/loopQualitylow risknew

Keep wiki health green

Run wiki-linter on a cadence to catch and fix frontmatter drift, stopping when all checks pass.

prompt
→ Claude Code
/loop 1h /triage (or self-paced, no interval; equivalently, "run wiki-linter for a full health-check pass"). Safe fully unattended: wiki-linter only writes to wiki/issues.md, never edits page content beyond mechanical frontmatter fixes, and never calls AskUserQuestion — every iteration completes without a human present