Review preparation

Input: variant=code-review|team-review|pr-review, target, original entry flags, output root; optionally the caller's resolved scope, baseline and candidate bindings. Output: resolved target and snapshot, native review brief, context files, reviewer selection, run identity and evidence discovery.

Load the project-protocol:project-protocol skill for execution preflight and confined run records. A read-only review may use a dirty workspace: record its complete snapshot and preserve existing edits. Do not create a mutation authorization by reviewing.

A caller-bound candidate is authoritative. Validate its project/worktree, run, scope and current snapshot through project-protocol before deriving review inputs. Use its captured baseline and exact candidate content, including scoped untracked files and their full contents. Exclude the run's output root. Never replace that target with a branch comparison or the previous commit. Missing baseline content is a declared comparison gap, not permission to invent a before-state; preserve the actual candidate and leave any gate needing that comparison unavailable.