repo-harness-check

# repo-harness-check Use this command when the user asks whether the harness, migration, or release surface is ready. ## Protocol 1. Confirm the repo path and report dirty-worktree boundaries. 2. Read the canonical required-check list from the target repo's root agent context (`CLAUDE.md` for Claude, `AGENTS.md` for Codex) `## Required Checks` section, then run every command listed there through the global/package helper runtime. This self-host source repo may also use root `scripts/` for source-only maintenance commands. Example only, not a fixed list: `bun test`. If `## Required Checks` is missing or empty, report that as the first blocking finding instead of substituting a default list. 3. Run advisory readiness when available: - `repo-harness run check-agent-tooling --host both --json` 4. Treat missing CodeGraph or missing Codex `health`/`check`/`mermaid` as hard failures. 5. Treat Waza staging drift as a yellow readiness flag; report the fix or acceptance reason without failing the repo gate. 6. Report skill eval authority when release/readiness evidence depends on skill effectiveness: - authoritative: non-dry-run `bun run benchmark:skills --eval <slug>` with `full_test_count > 0`, `dry_run_ratio <= 30%`, and graders reported - non-authoritative: dry-run-heavy or all-dry-run evidence - unavailable: no current eval evidence; report the benchmark command needed 7. Summarize pass/fail evidence, yellow flags, eval authority metrics, and the next blocki...