cross-reviewlisted
Install: claude install-skill Smart-AI-Memory/attune-ai
# Cross Review
**IMPORTANT: Start your response by telling the user:**
> **Cross review** — one non-authoring seat reviews the real diff.
> Advisory only: findings inform you; they never gate anything.
## Binding posture (spec requirement, not style)
Board-only ADVISORY. Never wire this skill's output into a merge
gate, CI check, exit code, or blocking path — that violates
`docs/specs/cross-review/requirements.md` (Binding posture). Only a
chair ruling backed by the spec's dogfood ledger can upgrade it.
## What it does
Phase T2 of `docs/specs/cross-review/`: the moderator (this
session) resolves the current branch's diff vs its merge base
(default) or the staged diff, briefs ONE non-authoring seat with
the ACTUAL diff under an honest truncation manifest, posts the
reply to the board, renders findings as advisory items, and
appends a dogfood-ledger row. All mechanics live in
`attune.roundtable.review` — do not reimplement them inline.
## Steps
1. **Spend gate**: state seat + target (one line) and get a go
(session-durable, same rule as `/roundtable`).
An existing explicit review request is the go for that seat/target.
For an explicitly requested Claude subscription review, use
`seat="claude", claude_auth="subscription"`. The launcher checks saved
Pro/Max authentication in a child with API credentials removed, disables
tools/custom integrations, and refuses ambiguous/API authentication.
It does not raise or disable the API spend cap or modify intera