codex-adversarial-reviewlisted

# Codex adversarial review Use the companion's built-in `adversarial-review` command, not a hand-written Codex CLI call. The companion runs the review with a `read-only` sandbox and tracks it as a job. This is a challenge review: inspect chosen boundaries, assumptions, failure modes, and trade-offs, not only local defects. ## Before the first run of a session Read **[`references/codex-runtime.md`](references/codex-runtime.md)** (same directory). It holds the family-level mechanics shared with `codex-implement` — companion resolution, the `--background` launcher-output trap, `status` lying about liveness, the lossy-pipe report loss, report recovery from session rollouts, sandbox limits, and the model/effort plumbing. Every item was paid for with an incident; this file assumes them and covers only what makes a run a *review*. ## Establish an immutable review target **One frozen directory per reviewer, at the exact commit, that nothing else touches — no lead activity inside it.** Not "whenever possible": a reviewer reads the WORKING TREE, not your commit. Measured — a round ran mutation testing in the same worktree mid-review and the reviewer opened a CRITICAL on a mutated, non-compiling file it was never meant to see. Freeze it with the suite's tested helpers instead of hand-rolling the shell; every bug ever found in this step was in a hand-rolled copy. The suite-root resolver and both calls — `freeze-target.sh` to create it, `verify-target.sh` before AND after the run —