po-council

# Atlas PO review — two critics, one accountable owner The active pilot does not summon a standing committee. `pnpm po:route` derives the primary risk from change facts and all four boundary assessments, then selects Evidence plus exactly one specialist. The human owner decides. ## Reviewer map | Derived risk | Required reviewers | Independent question | |---|---|---| | `meaning` | `po-evidence` + `po-steward` | Is the lost human ability observed, and do meaning, evidence truth, local-first behavior, agent authority, and correction stay trustworthy? | | `positioning` | `po-evidence` + `po-wedge` | Is the lost ability observed, and is the first-contact claim distinctive and earned? | | `scope` | `po-evidence` + `po-leverage` | Is the lost ability observed, and is this the smallest worthwhile commitment with a credible rollback? | `po-craft` is owner-requested recovery-proof review only. It consumes evidence from the design, responsive, motion, and walkthrough gates; it does not repeat them. Seat briefs live at `../../agents/po-*.md`. Open only the selected files. From either mirrored skill tree, the relative path resolves to the matching agent tree. Never create a third copy. Run the selected pair in separate contexts and give neither the other's output before first positions are sealed. Use parallel scheduling when available; serial scheduling alone does not weaken independent contexts. If separate contexts are unavailable, disclose the missing independence and report a...